diff options
Diffstat (limited to 'tools/bpf')
23 files changed, 2164 insertions, 194 deletions
diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore new file mode 100644 index 000000000000..dfe2bd5a4b95 --- /dev/null +++ b/tools/bpf/.gitignore @@ -0,0 +1,5 @@ +FEATURE-DUMP.bpf +bpf_asm +bpf_dbg +bpf_exp.yacc.* +bpf_jit_disasm diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers new file mode 100644 index 000000000000..c34fea77f39f --- /dev/null +++ b/tools/bpf/Makefile.helpers @@ -0,0 +1,59 @@ +ifndef allow-override + include ../scripts/Makefile.include + include ../scripts/utilities.mak +else + # Assume Makefile.helpers is being run from bpftool/Documentation + # subdirectory. Go up two more directories to fetch bpf.h header and + # associated script. + UP2DIR := ../../ +endif + +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 +man7dir = $(mandir)/man7 + +HELPERS_RST = bpf-helpers.rst +MAN7_RST = $(HELPERS_RST) + +_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST)) +DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7)) + +helpers: man7 +man7: $(DOC_MAN7) + +RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) + +$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h + $(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@ + +$(OUTPUT)%.7: $(OUTPUT)%.rst +ifndef RST2MAN_DEP + $(error "rst2man not found, but required to generate man pages") +endif + $(QUIET_GEN)rst2man $< > $@ + +helpers-clean: + $(call QUIET_CLEAN, eBPF_helpers-manpage) + $(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST) + +helpers-install: helpers + $(call QUIET_INSTALL, eBPF_helpers-manpage) + $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir) + $(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) + +helpers-uninstall: + $(call QUIET_UNINST, eBPF_helpers-manpage) + $(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7)) + $(Q)$(RMDIR) $(DESTDIR)$(man7dir) + +.PHONY: helpers helpers-clean helpers-install helpers-uninstall diff --git a/tools/bpf/bpf_exp.l b/tools/bpf/bpf_exp.l index bd83149e7be0..4da8d053d68f 100644 --- a/tools/bpf/bpf_exp.l +++ b/tools/bpf/bpf_exp.l @@ -175,7 +175,7 @@ extern void yyerror(const char *str); yylval.number = strtol(yytext, NULL, 10); return number; } -([0][0-9]+) { +([0][0-7]+) { yylval.number = strtol(yytext + 1, NULL, 8); return number; } diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore new file mode 100644 index 000000000000..67167e44b726 --- /dev/null +++ b/tools/bpf/bpftool/.gitignore @@ -0,0 +1,5 @@ +*.d +bpftool +bpftool*.8 +bpf-helpers.* +FEATURE-DUMP.bpftool diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index a9d47c1558bb..f7663a3e60c9 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -15,12 +15,15 @@ prefix ?= /usr/local mandir ?= $(prefix)/man man8dir = $(mandir)/man8 -MAN8_RST = $(wildcard *.rst) +# Load targets for building eBPF helpers man page. +include ../../Makefile.helpers + +MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst)) _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) -man: man8 +man: man8 helpers man8: $(DOC_MAN8) RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) @@ -31,16 +34,16 @@ ifndef RST2MAN_DEP endif $(QUIET_GEN)rst2man $< > $@ -clean: +clean: helpers-clean $(call QUIET_CLEAN, Documentation) $(Q)$(RM) $(DOC_MAN8) -install: man +install: man helpers-install $(call QUIET_INSTALL, Documentation-man) $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir) $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir) -uninstall: +uninstall: helpers-uninstall $(call QUIET_UNINST, Documentation-man) $(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8)) $(Q)$(RMDIR) $(DESTDIR)$(man8dir) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 0e4e923235b6..edbe81534c6d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -15,18 +15,21 @@ SYNOPSIS *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } *COMMANDS* := - { **show** | **list** | **attach** | **detach** | **help** } + { **show** | **list** | **tree** | **attach** | **detach** | **help** } MAP COMMANDS ============= | **bpftool** **cgroup { show | list }** *CGROUP* +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] | **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* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } +| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | +| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | +| **sendmsg4** | **sendmsg6** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -37,6 +40,15 @@ DESCRIPTION Output will start with program ID followed by attach type, attach flags and program name. + **bpftool cgroup tree** [*CGROUP_ROOT*] + 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. + **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*. @@ -63,7 +75,17 @@ DESCRIPTION **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). + **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). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 457e868bd32f..a6258bc8ec4f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -22,17 +22,19 @@ MAP COMMANDS ============= | **bpftool** **map { show | list }** [*MAP*] -| **bpftool** **map dump** *MAP* -| **bpftool** **map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] -| **bpftool** **map lookup** *MAP* **key** *BYTES* -| **bpftool** **map getnext** *MAP* [**key** *BYTES*] -| **bpftool** **map delete** *MAP* **key** *BYTES* -| **bpftool** **map pin** *MAP* *FILE* +| **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 help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *DATA* := { [**hex**] *BYTES* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *VALUE* := { *BYTES* | *MAP* | *PROG* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } DESCRIPTION @@ -48,20 +50,26 @@ DESCRIPTION **bpftool map dump** *MAP* Dump all entries in a given *MAP*. - **bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] + **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. - **bpftool map lookup** *MAP* **key** *BYTES* + If the **hex** keyword is provided in front of the bytes + sequence, the bytes are parsed as hexadeximal 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** *BYTES*] + **bpftool map getnext** *MAP* [**key** *DATA*] Get next key. If *key* is not specified, get first key. - **bpftool map delete** *MAP* **key** *BYTES* + **bpftool map delete** *MAP* **key** *DATA* Remove entry from the map. **bpftool map pin** *MAP* *FILE* @@ -69,6 +77,22 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. + **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 help** Print short help message. @@ -98,7 +122,12 @@ EXAMPLES 10: hash name some_map flags 0x0 key 4B value 8B max_entries 2048 memlock 167936B -**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** +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** diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst new file mode 100644 index 000000000000..e3eb0eab7641 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -0,0 +1,81 @@ +================ +bpftool-perf +================ +------------------------------------------------------------------------------- +tool for inspection of perf related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **perf** *COMMAND* + + *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + + *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 +======= + -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**. + +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}] + + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 67ca6c69376c..64156a16d530 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -24,10 +24,20 @@ MAP COMMANDS | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog load** *OBJ* *FILE* +| **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] | **bpftool** **prog help** | +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *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/sendmsg4** | **cgroup/sendmsg6** +| } + DESCRIPTION =========== @@ -64,8 +74,19 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. - **bpftool prog load** *OBJ* *FILE* + **bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] Load bpf program from binary *OBJ* and pin as *FILE*. + **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). Note: *FILE* must be located in *bpffs* mount. @@ -95,7 +116,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 005a3d2123620c8b + 10: xdp name some_prog tag 005a3d2123620c8b gpl loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 @@ -108,6 +129,7 @@ EXAMPLES "id": 10, "type": "xdp", "tag": "005a3d2123620c8b", + "gpl_compatible": true, "loaded_at": "Sep 29/20:11", "uid": 0, "bytes_xlated": 528, @@ -158,6 +180,14 @@ EXAMPLES 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** +| SEE ALSO ======== diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 20689a321ffe..b6f5d560460d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -16,20 +16,22 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** } + *OBJECT* := { **map** | **program** | **cgroup** | **perf** } *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } | { **-j** | **--json** } [{ **-p** | **--pretty** }] } *MAP-COMMANDS* := { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **help** } + | **pin** | **event_pipe** | **help** } *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **help** } *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + *PERF-COMMANDS* := { **show** | **list** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects @@ -56,3 +58,4 @@ OPTIONS SEE ALSO ======== **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4e69782c4a79..74288a2197ab 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -23,10 +23,10 @@ endif LIBBPF = $(BPF_PATH)libbpf.a -BPFTOOL_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion) +BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) @@ -39,7 +39,12 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers -CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' LIBS = -lelf -lbfd -lopcodes $(LIBBPF) @@ -47,7 +52,7 @@ INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args reallocarray FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 @@ -70,6 +75,10 @@ ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif +ifeq ($(feature-reallocarray), 0) +CFLAGS += -DCOMPAT_NEED_REALLOCARRAY +endif + include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 490811b45fa7..598066c40191 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1,6 +1,6 @@ # bpftool(8) bash completion -*- shell-script -*- # -# Copyright (C) 2017 Netronome Systems, Inc. +# Copyright (C) 2017-2018 Netronome Systems, Inc. # # This software is dual licensed under the GNU General License # Version 2, June 1991 as shown in the file COPYING in the top-level @@ -79,6 +79,14 @@ _bpftool_get_map_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_perf_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 perf_event_array | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -91,6 +99,35 @@ _bpftool_get_prog_tags() command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$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" ) ) +} + # For bpftool map update: retrieve type of the map to update. _bpftool_map_update_map_type() { @@ -145,9 +182,16 @@ _bpftool() local cur prev words objword _init_completion || return + # Deal with options + if [[ ${words[cword]} == -* ]]; then + local c='--version --json --pretty --bpffs' + COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) + return 0 + fi + # Deal with simplest keywords case $prev in - help|key|opcodes|visual) + help|hex|opcodes|visual) return 0 ;; tag) @@ -164,20 +208,23 @@ _bpftool() ;; esac - # Search for object and command - local object command cmdword - for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do - [[ -n $object ]] && command=${words[cmdword]} && break - [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]} + # Remove all options so completions don't have to deal with them. + local i + for (( i=1; i < ${#words[@]}; )); do + if [[ ${words[i]::1} == - ]]; then + words=( "${words[@]:0:i}" "${words[@]:i+1}" ) + [[ $i -le $cword ]] && cword=$(( cword - 1 )) + else + i=$(( ++i )) + fi done + cur=${words[cword]} + prev=${words[cword - 1]} + + local object=${words[1]} command=${words[2]} - if [[ -z $object ]]; then + if [[ -z $object || $cword -eq 1 ]]; then case $cur in - -*) - local c='--version --json --pretty' - COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) - return 0 - ;; *) COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \ command sed \ @@ -196,12 +243,14 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - case $prev in - id) - _bpftool_get_prog_ids - return 0 - ;; - esac + if [[ $command != "load" ]]; then + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + esac + fi local PROG_TYPE='id pinned tag' case $command in @@ -244,8 +293,57 @@ _bpftool() return 0 ;; load) - _filedir - return 0 + local obj + + 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) + COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \ + "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + return 0 + ;; + pinned) + _filedir + return 0 + ;; + dev) + _sysfs_get_netdevs + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) + _bpftool_once_attr 'type' + _bpftool_once_attr 'dev' + return 0 + ;; + esac ;; *) [[ $prev == $object ]] && \ @@ -283,7 +381,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; *) _bpftool_once_attr 'key' @@ -302,7 +400,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; value) # We can have bytes, or references to a prog or a @@ -321,6 +419,8 @@ _bpftool() return 0 ;; *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) return 0 ;; esac @@ -357,10 +457,34 @@ _bpftool() fi return 0 ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_perf_map_ids + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu' + _bpftool_once_attr 'index' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ - lookup pin show list update' -- "$cur" ) ) + lookup pin event_pipe show list update' -- \ + "$cur" ) ) ;; esac ;; @@ -370,9 +494,14 @@ _bpftool() _filedir return 0 ;; + tree) + _filedir + return 0 + ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ - device' + device bind4 bind6 post_bind4 post_bind6 connect4 \ + connect6 sendmsg4 sendmsg6' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -380,7 +509,9 @@ _bpftool() _filedir return 0 ;; - ingress|egress|sock_create|sock_ops|device) + ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ + post_bind4|post_bind6|connect4|connect6|sendmsg4|\ + sendmsg6) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 @@ -408,6 +539,15 @@ _bpftool() *) [[ $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 diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c new file mode 100644 index 000000000000..55bc512a1831 --- /dev/null +++ b/tools/bpf/bpftool/btf_dumper.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ + +#include <ctype.h> +#include <stdio.h> /* for (FILE *) used by json_writer */ +#include <string.h> +#include <asm/byteorder.h> +#include <linux/bitops.h> +#include <linux/btf.h> +#include <linux/err.h> + +#include "btf.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 void btf_dumper_ptr(const void *data, json_writer_t *jw, + bool is_plain_text) +{ + if (is_plain_text) + jsonw_printf(jw, "%p", *(unsigned long *)data); + else + jsonw_printf(jw, "%u", *(unsigned long *)data); +} + +static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, + 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, 0, data); +} + +static void btf_dumper_enum(const void *data, json_writer_t *jw) +{ + jsonw_printf(jw, "%d", *(int *)data); +} + +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; + + 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_dumper_int_bits(__u32 int_type, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int left_shift_bits, right_shift_bits; + int nr_bits = BTF_INT_BITS(int_type); + int total_bits_offset; + int bytes_to_copy; + int bits_to_copy; + __u64 print_num; + + 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); + bits_to_copy = bit_offset + nr_bits; + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy); + + print_num = 0; + 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 = 64 - bits_to_copy; +#else +#error neither big nor little endian +#endif + right_shift_bits = 64 - nr_bits; + + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; + if (is_plain_text) + jsonw_printf(jw, "0x%llx", print_num); + else + jsonw_printf(jw, "%llu", print_num); +} + +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; + } + + switch (BTF_INT_ENCODING(*int_type)) { + case 0: + if (BTF_INT_BITS(*int_type) == 64) + jsonw_printf(jw, "%lu", *(__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, "%ld", *(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, *(int *)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 ret = 0; + int i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + jsonw_start_object(d->jw); + m = (struct btf_member *)(t + 1); + + for (i = 0; i < vlen; i++) { + data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset); + jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off)); + ret = btf_dumper_do_type(d, m[i].type, + BITS_PER_BYTE_MASKED(m[i].offset), + data_off); + if (ret) + break; + } + + 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: + btf_dumper_enum(data, d->jw); + return 0; + case BTF_KIND_PTR: + btf_dumper_ptr(data, d->jw, d->is_plain_text); + 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, 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); +} diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index cae32a61cb18..ee7a9765c6b3 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -2,7 +2,12 @@ // 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> @@ -16,8 +21,11 @@ #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - "ATTACH_TYPE := { ingress | egress | sock_create | sock_ops | device }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ + " sock_ops | device | bind4 | bind6 |\n" \ + " post_bind4 | post_bind6 | connect4 |\n" \ + " connect6 | sendmsg4 | sendmsg6 }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -25,6 +33,14 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", [BPF_CGROUP_SOCK_OPS] = "sock_ops", [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", + [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", + [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -42,7 +58,8 @@ static enum bpf_attach_type parse_attach_type(const char *str) } static int show_bpf_prog(int id, const char *attach_type_str, - const char *attach_flags_str) + const char *attach_flags_str, + int level) { struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); @@ -67,7 +84,8 @@ static int show_bpf_prog(int id, const char *attach_type_str, jsonw_string_field(json_wtr, "name", info.name); jsonw_end_object(json_wtr); } else { - printf("%-8u %-15s %-15s %-15s\n", info.id, + printf("%s%-8u %-15s %-15s %-15s\n", level ? " " : "", + info.id, attach_type_str, attach_flags_str, info.name); @@ -77,7 +95,20 @@ static int show_bpf_prog(int id, const char *attach_type_str, return 0; } -static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) +static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) +{ + __u32 prog_cnt = 0; + int ret; + + ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + if (ret) + return -1; + + return prog_cnt; +} + +static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) { __u32 prog_ids[1024] = {0}; char *attach_flags_str; @@ -112,7 +143,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) for (iter = 0; iter < prog_cnt; iter++) show_bpf_prog(prog_ids[iter], attach_type_strings[type], - attach_flags_str); + attach_flags_str, level); return 0; } @@ -150,7 +181,7 @@ static int do_show(int argc, char **argv) * If we were able to get the show for at least one * attach type, let's return 0. */ - if (show_attached_bpf_progs(cgroup_fd, type) == 0) + if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0) ret = 0; } @@ -162,6 +193,143 @@ 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; + bool skip = true; + 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; + } + + 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) { + 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); + } + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) + show_attached_bpf_progs(cgroup_fd, type, ftw->level); + + 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; + int ret; + + switch (argc) { + case 0: + cgroup_root = find_cgroup_root(); + if (!cgroup_root) { + p_err("cgroup v2 isn't mounted"); + return -1; + } + break; + case 1: + cgroup_root = argv[0]; + break; + default: + p_err("too many parameters for cgroup tree"); + return -1; + } + + + if (json_output) + jsonw_start_array(json_wtr); + 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); + + if (argc == 0) + free(cgroup_root); + + return ret; +} + static int do_attach(int argc, char **argv) { enum bpf_attach_type attach_type; @@ -278,15 +446,17 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } CGROUP\n" + " %s %s tree [CGROUP_ROOT]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" "\n" - " " HELP_SPEC_ATTACH_TYPES "\n" + HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); @@ -296,6 +466,7 @@ static int do_help(int argc, char **argv) static const struct cmd cmds[] = { { "show", do_show }, { "list", do_show }, + { "tree", do_show_tree }, { "attach", do_attach }, { "detach", do_detach }, { "help", do_help }, diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 465995281dcd..b3a0709ea7ed 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -31,8 +31,7 @@ * SOFTWARE. */ -/* Author: Jakub Kicinski <kubakici@wp.pl> */ - +#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <fts.h> @@ -216,6 +215,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) int err; int fd; + if (argc < 3) { + p_err("too few arguments, id ID and FILE path is required"); + return -1; + } else if (argc > 3) { + p_err("too many arguments"); + return -1; + } + if (!is_prefix(*argv, "id")) { p_err("expected 'id' got %s", *argv); return -1; @@ -229,9 +236,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) } NEXT_ARG(); - if (argc != 1) - usage(); - fd = get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); @@ -330,6 +334,16 @@ char *get_fdinfo(int fd, const char *key) 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; @@ -420,6 +434,70 @@ void delete_pinned_obj_table(struct pinned_obj_table *tab) } } +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + static unsigned int result; + char buf[128]; + long int n; + char *ptr; + int fd; + + if (result) + return result; + + fd = open("/sys/devices/system/cpu/possible", O_RDONLY); + if (fd < 0) { + p_err("can't open sysfs possible cpus"); + exit(-1); + } + + n = read(fd, buf, sizeof(buf)); + if (n < 2) { + p_err("can't read sysfs possible cpus"); + exit(-1); + } + close(fd); + + if (n == sizeof(buf)) { + p_err("read sysfs possible cpus overflow"); + exit(-1); + } + + ptr = buf; + n = 0; + while (*ptr && *ptr != '\n') { + unsigned int a, b; + + if (sscanf(ptr, "%u-%u", &a, &b) == 2) { + n += b - a + 1; + + ptr = strchr(ptr, '-') + 1; + } else if (sscanf(ptr, "%u", &a) == 1) { + n++; + } else { + assert(0); + } + + while (isdigit(*ptr)) + ptr++; + if (*ptr == ',') + ptr++; + } + + result = n; + + return result; +} + static char * ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) { diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 1ec852d21d44..d15a62be6cf0 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -31,8 +31,6 @@ * SOFTWARE. */ -/* Author: Jakub Kicinski <kubakici@wp.pl> */ - #include <bfd.h> #include <ctype.h> #include <errno.h> @@ -87,7 +85,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup }\n" + " OBJECT := { prog | map | cgroup | perf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -216,6 +214,7 @@ static const struct cmd cmds[] = { { "prog", do_prog }, { "map", do_map }, { "cgroup", do_cgroup }, + { "perf", do_perf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index b8e9584d6246..238e734d75b3 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -31,8 +31,6 @@ * SOFTWARE. */ -/* Author: Jakub Kicinski <kubakici@wp.pl> */ - #ifndef __BPF_TOOL_H #define __BPF_TOOL_H @@ -44,6 +42,7 @@ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/hashtable.h> +#include <tools/libc_compat.h> #include "json_writer.h" @@ -52,6 +51,21 @@ #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 @@ -61,6 +75,8 @@ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" #define HELP_SPEC_OPTIONS \ "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }" +#define HELP_SPEC_MAP \ + "MAP := { id MAP_ID | pinned FILE }" enum bpf_obj_type { BPF_OBJ_UNKNOWN, @@ -117,14 +133,36 @@ int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); int do_map(int argc, char **arg); +int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); +int do_perf(int argc, char **arg); int prog_parse_fd(int *argc, char ***argv); +int map_parse_fd(int *argc, char ***argv); +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch); +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_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); +struct btf_dumper { + const struct btf *btf; + json_writer_t *jw; + bool is_plain_text; +}; + +/* 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); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index f509c86faede..b455930a3eaf 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -31,12 +31,11 @@ * SOFTWARE. */ -/* Author: Jakub Kicinski <kubakici@wp.pl> */ - #include <assert.h> -#include <ctype.h> #include <errno.h> #include <fcntl.h> +#include <linux/err.h> +#include <linux/kernel.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -47,6 +46,8 @@ #include <bpf.h> +#include "btf.h" +#include "json_writer.h" #include "main.h" static const char * const map_type_name[] = { @@ -67,63 +68,11 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_DEVMAP] = "devmap", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", + [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", }; -static unsigned int get_possible_cpus(void) -{ - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); - - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); - exit(-1); - } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; -} - static bool map_is_per_cpu(__u32 type) { return type == BPF_MAP_TYPE_PERCPU_HASH || @@ -145,12 +94,13 @@ static bool map_is_map_of_progs(__u32 type) static void *alloc_value(struct bpf_map_info *info) { if (map_is_per_cpu(info->type)) - return malloc(info->value_size * get_possible_cpus()); + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); else return malloc(info->value_size); } -static int map_parse_fd(int *argc, char ***argv) +int map_parse_fd(int *argc, char ***argv) { int fd; @@ -186,8 +136,7 @@ static int map_parse_fd(int *argc, char ***argv) return -1; } -static int -map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; int fd; @@ -206,8 +155,109 @@ map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) return fd; } +static int do_dump_btf(const struct btf_dumper *d, + struct bpf_map_info *map_info, void *key, + void *value) +{ + int ret; + + /* start of key-value pair */ + jsonw_start_object(d->jw); + + jsonw_name(d->jw, "key"); + + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + + jsonw_name(d->jw, "value"); + + ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + +err_end_obj: + /* end of key-value pair */ + jsonw_end_object(d->jw); + + return ret; +} + +static int get_btf(struct bpf_map_info *map_info, struct btf **btf) +{ + struct bpf_btf_info btf_info = { 0 }; + __u32 len = sizeof(btf_info); + __u32 last_size; + int btf_fd; + void *ptr; + int err; + + err = 0; + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id); + if (btf_fd < 0) + return 0; + + /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + * let's start with a sane default - 4KiB here - and resize it only if + * bpf_obj_get_info_by_fd() needs a bigger buffer. + */ + btf_info.btf_size = 4096; + last_size = btf_info.btf_size; + ptr = malloc(last_size); + if (!ptr) { + err = -ENOMEM; + goto exit_free; + } + + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + + if (!err && btf_info.btf_size > last_size) { + void *temp_ptr; + + last_size = btf_info.btf_size; + temp_ptr = realloc(ptr, last_size); + if (!temp_ptr) { + err = -ENOMEM; + goto exit_free; + } + ptr = temp_ptr; + bzero(ptr, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + } + + if (err || btf_info.btf_size > last_size) { + err = errno; + goto exit_free; + } + + *btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + } + +exit_free: + close(btf_fd); + free(ptr); + + return err; +} + +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) + unsigned char *value, struct btf *btf) { jsonw_start_object(json_wtr); @@ -216,10 +266,21 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *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; + 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); @@ -232,7 +293,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_int_field(json_wtr, "cpu", i); jsonw_name(json_wtr, "value"); - print_hex_data_json(value + i * info->value_size, + print_hex_data_json(value + i * step, info->value_size); jsonw_end_object(json_wtr); @@ -263,9 +324,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, printf("\n"); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); printf("key:\n"); fprint_hex(stdout, key, info->key_size, " "); @@ -273,7 +335,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - fprint_hex(stdout, value + i * info->value_size, + fprint_hex(stdout, value + i * step, info->value_size, " "); printf("\n"); } @@ -283,11 +345,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, static char **parse_bytes(char **argv, const char *name, unsigned char *val, unsigned int n) { - unsigned int i = 0; + 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, 0); + val[i] = strtoul(argv[i], &endptr, base); if (*endptr) { p_err("error parsing byte: %s", argv[i]); return NULL; @@ -561,10 +628,12 @@ static int do_show(int argc, char **argv) static int do_dump(int argc, char **argv) { + struct bpf_map_info info = {}; void *key, *value, *prev_key; unsigned int num_elems = 0; - struct bpf_map_info info = {}; __u32 len = sizeof(info); + json_writer_t *btf_wtr; + struct btf *btf = NULL; int err; int fd; @@ -590,8 +659,27 @@ static int do_dump(int argc, char **argv) } prev_key = NULL; + + err = get_btf(&info, &btf); + if (err) { + p_err("failed to get 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); + } + } + while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -602,9 +690,19 @@ static int do_dump(int argc, char **argv) if (!bpf_map_lookup_elem(fd, key, value)) { if (json_output) - print_entry_json(&info, key, value); + print_entry_json(&info, key, value, btf); else - print_entry_plain(&info, key, value); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, &info, key, value); + } else { + print_entry_plain(&info, key, value); + } } else { if (json_output) { jsonw_name(json_wtr, "key"); @@ -627,14 +725,19 @@ static int do_dump(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - else + else if (btf) { + jsonw_end_array(btf_wtr); + jsonw_destroy(&btf_wtr); + } else { printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); + } exit_free: free(key); free(value); close(fd); + btf__free(btf); return err; } @@ -690,6 +793,8 @@ static int do_lookup(int argc, char **argv) { struct bpf_map_info info = {}; __u32 len = sizeof(info); + json_writer_t *btf_wtr; + struct btf *btf = NULL; void *key, *value; int err; int fd; @@ -714,27 +819,60 @@ static int do_lookup(int argc, char **argv) goto exit_free; err = bpf_map_lookup_elem(fd, key, value); - if (!err) { - if (json_output) - print_entry_json(&info, key, value); - else + 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 */ + err = get_btf(&info, &btf); + if (err) { + p_err("failed to get btf"); + goto exit_free; + } + + 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 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"); + 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 { - p_err("lookup failed: %s", strerror(errno)); + print_entry_plain(&info, key, value); } exit_free: free(key); free(value); close(fd); + btf__free(btf); return err; } @@ -868,23 +1006,25 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [MAP]\n" - " %s %s dump MAP\n" - " %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" - " %s %s lookup MAP key BYTES\n" - " %s %s getnext MAP [key BYTES]\n" - " %s %s delete MAP key BYTES\n" - " %s %s pin MAP FILE\n" + " %s %s dump MAP\n" + " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n" + " %s %s lookup MAP key DATA\n" + " %s %s getnext MAP [key DATA]\n" + " %s %s delete MAP key DATA\n" + " %s %s pin MAP FILE\n" + " %s %s event_pipe MAP [cpu N index M]\n" " %s %s help\n" "\n" - " MAP := { id MAP_ID | pinned FILE }\n" + " " HELP_SPEC_MAP "\n" + " DATA := { [hex] BYTES }\n" " " HELP_SPEC_PROGRAM "\n" - " VALUE := { BYTES | MAP | PROG }\n" + " VALUE := { DATA | MAP | PROG }\n" " UPDATE_FLAGS := { any | exist | noexist }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -899,6 +1039,7 @@ static const struct cmd cmds[] = { { "getnext", do_getnext }, { "delete", do_delete }, { "pin", do_pin }, + { "event_pipe", do_event_pipe }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 000000000000..6d41323be291 --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* 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 <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.h> +#include <perf-sys.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static bool stop; + +struct event_ring_info { + int fd; + int key; + unsigned int cpu; + void *mem; +}; + +struct perf_event_sample { + struct perf_event_header header; + u64 time; + __u32 size; + unsigned char data[]; +}; + +static void int_exit(int signo) +{ + fprintf(stderr, "Stopping...\n"); + stop = true; +} + +static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv) +{ + struct event_ring_info *ring = priv; + struct perf_event_sample *e = event; + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = event; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "type"); + jsonw_uint(json_wtr, e->header.type); + jsonw_name(json_wtr, "cpu"); + jsonw_uint(json_wtr, ring->cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, ring->key); + 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, + ring->cpu, ring->key); + 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; +} + +static void +perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(ring->mem, + MMAP_PAGE_CNT * get_page_size(), + get_page_size(), buf, buf_len, + print_bpf_output, ring); + if (ret != LIBBPF_PERF_EVENT_CONT) { + fprintf(stderr, "perf read loop failed with %d\n", ret); + stop = true; + } +} + +static int perf_mmap_size(void) +{ + return get_page_size() * (MMAP_PAGE_CNT + 1); +} + +static void *perf_event_mmap(int fd) +{ + int mmap_size = perf_mmap_size(); + void *base; + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + p_err("event mmap failed: %s\n", strerror(errno)); + return NULL; + } + + return base; +} + +static void perf_event_unmap(void *mem) +{ + if (munmap(mem, perf_mmap_size())) + fprintf(stderr, "Can't unmap ring memory!\n"); +} + +static int bpf_perf_event_open(int map_fd, int key, int cpu) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int pmu_fd; + + pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + if (pmu_fd < 0) { + p_err("failed to open perf event %d for CPU %d", key, cpu); + return -1; + } + + if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { + p_err("failed to update map for event %d for CPU %d", key, cpu); + goto err_close; + } + if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + p_err("failed to enable event %d for CPU %d", key, cpu); + goto err_close; + } + + return pmu_fd; + +err_close: + close(pmu_fd); + return -1; +} + +int do_event_pipe(int argc, char **argv) +{ + int i, nfds, map_fd, index = -1, cpu = -1; + struct bpf_map_info map_info = {}; + struct event_ring_info *rings; + size_t tmp_buf_sz = 0; + void *tmp_buf = NULL; + struct pollfd *pfds; + __u32 map_info_len; + bool do_all = true; + + 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(); + 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(); + index = 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; + } + + do_all = false; + } + + if (!do_all) { + if (index == -1 || cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + + nfds = 1; + } else { + nfds = min(get_possible_cpus(), map_info.max_entries); + cpu = 0; + index = 0; + } + + rings = calloc(nfds, sizeof(rings[0])); + if (!rings) + goto err_close_map; + + pfds = calloc(nfds, sizeof(pfds[0])); + if (!pfds) + goto err_free_rings; + + for (i = 0; i < nfds; i++) { + rings[i].cpu = cpu + i; + rings[i].key = index + i; + + rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, + rings[i].cpu); + if (rings[i].fd < 0) + goto err_close_fds_prev; + + rings[i].mem = perf_event_mmap(rings[i].fd); + if (!rings[i].mem) + goto err_close_fds_current; + + pfds[i].fd = rings[i].fd; + pfds[i].events = POLLIN; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + poll(pfds, nfds, 200); + for (i = 0; i < nfds; i++) + perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + } + free(tmp_buf); + + if (json_output) + jsonw_end_array(json_wtr); + + for (i = 0; i < nfds; i++) { + perf_event_unmap(rings[i].mem); + close(rings[i].fd); + } + free(pfds); + free(rings); + close(map_fd); + + return 0; + +err_close_fds_prev: + while (i--) { + perf_event_unmap(rings[i].mem); +err_close_fds_current: + close(rings[i].fd); + } + free(pfds); +err_free_rings: + free(rings); +err_close_map: + close(map_fd); + return -1; +} diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c new file mode 100644 index 000000000000..b76b77dcfd1f --- /dev/null +++ b/tools/bpf/bpftool/perf.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0+ +// 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 <ftw.h> + +#include <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; + } + 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; + } +} + +static int show_proc(const char *fpath, const struct stat *sb, + int tflag, struct FTW *ftwbuf) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + int err, pid = 0, fd = 0; + const char *pch; + char buf[4096]; + + /* prefix always /proc */ + pch = fpath + 5; + if (*pch == '\0') + return 0; + + /* pid should be all numbers */ + pch++; + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd directory */ + pch++; + if (strncmp(pch, "fd", 2)) + return FTW_SKIP_SUBTREE; + pch += 2; + if (*pch == '\0') + return 0; + if (*pch != '/') + return FTW_SKIP_SUBTREE; + + /* check /proc/<pid>/fd/<fd_num> */ + pch++; + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + return FTW_SKIP_SUBTREE; + + /* 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) + return 0; + + 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); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + int flags = FTW_ACTIONRETVAL | FTW_PHYS; + int err = 0, nopenfd = 16; + + if (!has_perf_query_support()) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + if (nftw("/proc", show_proc, nopenfd, flags) == -1) { + p_err("%s", strerror(errno)); + err = -1; + } + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s { show | list | help }\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/prog.c b/tools/bpf/bpftool/prog.c index f7a810897eac..dce960d22106 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -31,8 +31,7 @@ * SOFTWARE. */ -/* Author: Jakub Kicinski <kubakici@wp.pl> */ - +#define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdarg.h> @@ -41,9 +40,12 @@ #include <string.h> #include <time.h> #include <unistd.h> +#include <net/if.h> #include <sys/types.h> #include <sys/stat.h> +#include <linux/err.h> + #include <bpf.h> #include <libbpf.h> @@ -68,6 +70,10 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", [BPF_PROG_TYPE_SK_SKB] = "sk_skb", [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", }; static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) @@ -86,14 +92,19 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) } wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + - nsecs / 1000000000; + (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; } - strftime(buf, size, "%b %d/%H:%M", &load_tm); + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); } static int prog_fd_by_tag(unsigned char *tag) @@ -232,6 +243,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) 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); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -240,7 +253,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) print_boot_time(info->load_time, buf, sizeof(buf)); /* Piggy back on load_time, since 0 uid is a valid one */ - jsonw_string_field(json_wtr, "loaded_at", buf); + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); jsonw_uint_field(json_wtr, "uid", info->created_by_uid); } @@ -292,6 +306,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) 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" : ""); printf("\n"); if (info->load_time) { @@ -410,7 +425,11 @@ static int do_show(int argc, char **argv) static int do_dump(int argc, char **argv) { + unsigned long *func_ksyms = NULL; struct bpf_prog_info info = {}; + unsigned int *func_lens = NULL; + unsigned int nr_func_ksyms; + unsigned int nr_func_lens; struct dump_data dd = {}; __u32 len = sizeof(info); unsigned int buf_size; @@ -486,10 +505,34 @@ static int do_dump(int argc, char **argv) return -1; } + nr_func_ksyms = info.nr_jited_ksyms; + if (nr_func_ksyms) { + func_ksyms = malloc(nr_func_ksyms * sizeof(__u64)); + if (!func_ksyms) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + + nr_func_lens = info.nr_jited_func_lens; + if (nr_func_lens) { + func_lens = malloc(nr_func_lens * sizeof(__u32)); + if (!func_lens) { + p_err("mem alloc failed"); + close(fd); + goto err_free; + } + } + memset(&info, 0, sizeof(info)); *member_ptr = ptr_to_u64(buf); *member_len = buf_size; + info.jited_ksyms = ptr_to_u64(func_ksyms); + info.nr_jited_ksyms = nr_func_ksyms; + info.jited_func_lens = ptr_to_u64(func_lens); + info.nr_jited_func_lens = nr_func_lens; err = bpf_obj_get_info_by_fd(fd, &info, &len); close(fd); @@ -503,6 +546,16 @@ static int do_dump(int argc, char **argv) goto err_free; } + if (info.nr_jited_ksyms > nr_func_ksyms) { + p_err("too many addresses returned"); + goto err_free; + } + + if (info.nr_jited_func_lens > nr_func_lens) { + p_err("too many values returned"); + goto err_free; + } + if ((member_len == &info.jited_prog_len && info.jited_prog_insns == 0) || (member_len == &info.xlated_prog_len && @@ -540,7 +593,57 @@ static int do_dump(int argc, char **argv) goto err_free; } - disasm_print_insn(buf, *member_len, opcodes, name); + if (info.nr_jited_func_lens && info.jited_func_lens) { + struct kernel_sym *sym = NULL; + 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 *) info.jited_ksyms; + } + + if (json_output) + jsonw_start_array(json_wtr); + + lens = (__u32 *) 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 (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "name"); + jsonw_string(json_wtr, sym_name); + jsonw_name(json_wtr, "insns"); + } else { + printf("%s:\n", sym_name); + } + + disasm_print_insn(img, lens[i], opcodes, name); + 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); + } } else if (visual) { if (json_output) jsonw_null(json_wtr); @@ -548,6 +651,9 @@ static int do_dump(int argc, char **argv) dump_xlated_cfg(buf, *member_len); } else { kernel_syms_load(&dd); + dd.nr_jited_ksyms = info.nr_jited_ksyms; + dd.jited_ksyms = (__u64 *) info.jited_ksyms; + if (json_output) dump_xlated_json(&dd, buf, *member_len, opcodes); else @@ -556,10 +662,14 @@ static int do_dump(int argc, char **argv) } free(buf); + free(func_ksyms); + free(func_lens); return 0; err_free: free(buf); + free(func_ksyms); + free(func_lens); return -1; } @@ -573,28 +683,248 @@ static int do_pin(int argc, char **argv) return err; } +struct map_replace { + int idx; + int fd; + char *name; +}; + +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 do_load(int argc, char **argv) { + enum bpf_attach_type expected_attach_type; + struct bpf_object_open_attr attr = { + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + struct map_replace *map_replace = NULL; + unsigned int old_map_fds = 0; + struct bpf_program *prog; struct bpf_object *obj; - int prog_fd; - - if (argc != 2) - usage(); + struct bpf_map *map; + const char *pinfile; + unsigned int i, j; + __u32 ifindex = 0; + int idx, err; - if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) { - p_err("failed to load program"); + if (!REQ_ARGS(2)) return -1; + attr.file = GET_ARG(); + pinfile = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "type")) { + char *type; + + NEXT_ARG(); + + if (attr.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; + + /* Put a '/' at the end of type to appease libbpf */ + 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 = libbpf_prog_type_by_name(type, &attr.prog_type, + &expected_attach_type); + free(type); + if (err < 0) { + p_err("unknown program type '%s'", *argv); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "map")) { + 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; + + map_replace = reallocarray(map_replace, old_map_fds + 1, + sizeof(*map_replace)); + if (!map_replace) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + 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 { + p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?", + *argv); + goto err_free_reuse_maps; + } } - if (do_pin_fd(prog_fd, argv[1])) { - p_err("failed to pin program"); - return -1; + obj = bpf_object__open_xattr(&attr); + if (IS_ERR_OR_NULL(obj)) { + p_err("failed to open object file"); + goto err_free_reuse_maps; + } + + prog = bpf_program__next(NULL, obj); + if (!prog) { + p_err("object file doesn't contain any bpf program"); + goto err_close_obj; + } + + bpf_program__set_ifindex(prog, ifindex); + if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) { + const char *sec_name = bpf_program__title(prog, false); + + err = libbpf_prog_type_by_name(sec_name, &attr.prog_type, + &expected_attach_type); + if (err < 0) { + p_err("failed to guess program type based on section name %s\n", + sec_name); + goto err_close_obj; + } } + bpf_program__set_type(prog, attr.prog_type); + bpf_program__set_expected_attach_type(prog, 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_map__for_each(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_map__for_each(map, obj) { + if (!bpf_map__is_offload_neutral(map)) + 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; + } + + if (do_pin_fd(bpf_program__fd(prog), pinfile)) + goto err_close_obj; 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_close_obj: + 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 do_help(int argc, char **argv) @@ -609,10 +939,19 @@ static int do_help(int argc, char **argv) " %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n" " %s %s dump jited PROG [{ file FILE | opcodes }]\n" " %s %s pin PROG FILE\n" - " %s %s load OBJ FILE\n" + " %s %s load OBJ FILE [type TYPE] [dev NAME] \\\n" + " [map { idx IDX | name NAME } MAP]\n" " %s %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" + " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" + " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" + " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7a3173b76c16..3284759df98a 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -35,6 +35,7 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#define _GNU_SOURCE #include <stdarg.h> #include <stdio.h> #include <stdlib.h> @@ -66,9 +67,8 @@ void kernel_syms_load(struct dump_data *dd) while (!feof(fp)) { if (!fgets(buff, sizeof(buff), fp)) break; - tmp = realloc(dd->sym_mapping, - (dd->sym_count + 1) * - sizeof(*dd->sym_mapping)); + tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); if (!tmp) { out: free(dd->sym_mapping); @@ -102,8 +102,8 @@ void kernel_syms_destroy(struct dump_data *dd) free(dd->sym_mapping); } -static struct kernel_sym *kernel_syms_search(struct dump_data *dd, - unsigned long key) +struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) { struct kernel_sym sym = { .address = key, @@ -174,7 +174,11 @@ static const char *print_call_pcrel(struct dump_data *dd, unsigned long address, const struct bpf_insn *insn) { - if (sym) + 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 @@ -203,6 +207,10 @@ static const char *print_call(void *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) + 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); diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index b34affa7ef2d..33d86e2b369b 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -49,11 +49,14 @@ struct dump_data { unsigned long address_call_base; struct kernel_sym *sym_mapping; __u32 sym_count; + __u64 *jited_ksyms; + __u32 nr_jited_ksyms; 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); void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, |
