diff options
Diffstat (limited to 'tools/bpf')
61 files changed, 9438 insertions, 2519 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 6df1850f8353..243b79f2b451 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -9,7 +9,8 @@ MAKE = make INSTALL ?= install CFLAGS += -Wall -O2 -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/include # This will work when bpf is built in tools env. where srctree # isn't set and when invoked from selftests build, where srctree @@ -33,11 +34,11 @@ else endif FEATURE_USER = .bpf -FEATURE_TESTS = libbfd disassembler-four-args -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled +FEATURE_DISPLAY = libbfd check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -55,6 +56,9 @@ endif ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif +ifeq ($(feature-disassembler-init-styled), 1) +CFLAGS += -DDISASM_INIT_STYLED +endif $(OUTPUT)%.yacc.c: $(srctree)/tools/bpf/%.y $(QUIET_BISON)$(YACC) -o $@ -d $< @@ -88,7 +92,7 @@ $(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 runqslower_clean +clean: bpftool_clean runqslower_clean resolve_btfids_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.* @@ -96,7 +100,7 @@ clean: bpftool_clean runqslower_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install runqslower_install +install: $(PROGS) bpftool_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 @@ -117,11 +121,15 @@ bpftool_clean: runqslower: $(call descend,runqslower) -runqslower_install: - $(call descend,runqslower,install) - runqslower_clean: $(call descend,runqslower,clean) +resolve_btfids: + $(call descend,resolve_btfids) + +resolve_btfids_clean: + $(call descend,resolve_btfids,clean) + .PHONY: all install clean bpftool bpftool_install bpftool_clean \ - runqslower runqslower_install runqslower_clean + runqslower runqslower_clean \ + resolve_btfids resolve_btfids_clean diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers deleted file mode 100644 index 854d084026dd..000000000000 --- a/tools/bpf/Makefile.helpers +++ /dev/null @@ -1,60 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -ifndef allow-override - include ../scripts/Makefile.include - include ../scripts/utilities.mak -else - # Assume Makefile.helpers is being run from bpftool/Documentation - # subdirectory. Go up two more directories to fetch bpf.h header and - # associated script. - UP2DIR := ../../ -endif - -INSTALL ?= install -RM ?= rm -f -RMDIR ?= rmdir --ignore-fail-on-non-empty - -ifeq ($(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_dbg.c b/tools/bpf/bpf_dbg.c index a0ebcdf59c31..00e560a17baf 100644 --- a/tools/bpf/bpf_dbg.c +++ b/tools/bpf/bpf_dbg.c @@ -890,7 +890,7 @@ static int bpf_run_stepping(struct sock_filter *f, uint16_t bpf_len, bool stop = false; int i = 1; - while (bpf_curr.Rs == false && stop == false) { + while (!bpf_curr.Rs && !stop) { bpf_safe_regs(); if (i++ == next) @@ -1198,7 +1198,7 @@ static int cmd_run(char *num) else return CMD_OK; bpf_reset(); - } while (pcap_next_pkt() && (!has_limit || (has_limit && ++i < pkts))); + } while (pcap_next_pkt() && (!has_limit || (++i < pkts))); rl_printf("bpf passes:%u fails:%u\n", pass, fail); diff --git a/tools/bpf/bpf_exp.y b/tools/bpf/bpf_exp.y index 8d48e896be50..dfb7254a24e8 100644 --- a/tools/bpf/bpf_exp.y +++ b/tools/bpf/bpf_exp.y @@ -185,13 +185,13 @@ ldx | OP_LDXB number '*' '(' '[' number ']' '&' number ')' { if ($2 != 4 || $9 != 0xf) { fprintf(stderr, "ldxb offset not supported!\n"); - exit(0); + exit(1); } else { bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } } | OP_LDX number '*' '(' '[' number ']' '&' number ')' { if ($2 != 4 || $9 != 0xf) { fprintf(stderr, "ldxb offset not supported!\n"); - exit(0); + exit(1); } else { bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } } ; @@ -472,7 +472,7 @@ static void bpf_assert_max(void) { if (curr_instr >= BPF_MAXINSNS) { fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS); - exit(0); + exit(1); } } @@ -522,7 +522,7 @@ static int bpf_find_insns_offset(const char *label) if (ret == -ENOENT) { fprintf(stderr, "no such label \'%s\'!\n", label); - exit(0); + exit(1); } return ret; @@ -549,9 +549,11 @@ static uint8_t bpf_encode_jt_jf_offset(int off, int i) { int delta = off - i - 1; - if (delta < 0 || delta > 255) - fprintf(stderr, "warning: insn #%d jumps to insn #%d, " + if (delta < 0 || delta > 255) { + fprintf(stderr, "error: insn #%d jumps to insn #%d, " "which is out of range\n", i, off); + exit(1); + } return (uint8_t) delta; } diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c index c8ae95804728..a90a5d110f92 100644 --- a/tools/bpf/bpf_jit_disasm.c +++ b/tools/bpf/bpf_jit_disasm.c @@ -28,6 +28,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <limits.h> +#include <tools/dis-asm-compat.h> #define CMD_ACTION_SIZE_BUFFER 10 #define CMD_ACTION_READ_ALL 3 @@ -64,7 +65,9 @@ static void get_asm_insns(uint8_t *image, size_t len, int opcodes) assert(bfdf); assert(bfd_check_format(bfdf, bfd_object)); - init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf); + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); info.arch = bfd_get_arch(bfdf); info.mach = bfd_get_mach(bfdf); info.buffer = image; diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 26cde83e1ca3..a736f64dc5dc 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,10 +1,10 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) *.d -/_bpftool +/bootstrap/ /bpftool bpftool*.8 -bpf-helpers.* FEATURE-DUMP.bpftool feature libbpf -profiler.skel.h +/*.skel.h +/vmlinux.h diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index 815ac9804aee..ac8487dcff1d 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -1,6 +1,5 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) include ../../../scripts/Makefile.include -include ../../../scripts/utilities.mak INSTALL ?= install RM ?= rm -f @@ -16,35 +15,43 @@ prefix ?= /usr/local mandir ?= $(prefix)/man man8dir = $(mandir)/man8 -# Load targets for building eBPF helpers man page. -include ../../Makefile.helpers - -MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst)) +MAN8_RST = $(wildcard bpftool*.rst) _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) -man: man8 helpers +man: man8 man8: $(DOC_MAN8) RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) +RST2MAN_OPTS += --verbose --strip-comments + +list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST)))) +see_also = $(subst " ",, \ + "\n" \ + "SEE ALSO\n" \ + "========\n" \ + "\t**bpf**\ (2),\n" \ + "\t**bpf-helpers**\\ (7)" \ + $(foreach page,$(call list_pages,$(1)),",\n\t**$(page)**\\ (8)") \ + "\n") $(OUTPUT)%.8: %.rst ifndef RST2MAN_DEP $(error "rst2man not found, but required to generate man pages") endif - $(QUIET_GEN)rst2man $< > $@ + $(QUIET_GEN)( cat $< ; printf "%b" $(call see_also,$<) ) | rst2man $(RST2MAN_OPTS) > $@ -clean: helpers-clean +clean: $(call QUIET_CLEAN, Documentation) $(Q)$(RM) $(DOC_MAN8) -install: man helpers-install +install: man $(call QUIET_INSTALL, Documentation-man) $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir) $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir) -uninstall: helpers-uninstall +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-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index ce3a724f50c1..342716f74ec4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-btf ================ @@ -7,12 +9,14 @@ tool for inspection of BTF data :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **btf** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } } *COMMANDS* := { **dump** | **help** } @@ -36,6 +40,11 @@ DESCRIPTION otherwise list all BTF objects currently loaded on the system. + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BTF + objects. On such kernels bpftool will automatically emit this + information as well. + **bpftool btf dump** *BTF_SRC* Dump BTF entries from a given *BTF_SRC*. @@ -66,26 +75,26 @@ DESCRIPTION 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. + .. include:: common_options.rst + + -B, --base-btf *FILE* + Pass a base BTF object. Base BTF objects are typically used + with BTF objects for kernel modules. To avoid duplicating + all kernel symbols required by modules, BTF objects for + modules are "split", they are built incrementally on top of + the kernel (vmlinux) BTF object. So the base BTF reference + should usually point to the kernel BTF. + + When the main BTF object to process (for example, the + module BTF to dump) is passed as a *FILE*, bpftool attempts + to autodetect the path for the base object, and passing + this option is optional. When the main BTF object is passed + through other handles, this option becomes necessary. EXAMPLES ======== **# bpftool btf dump id 1226** + :: [1] PTR '(anon)' type_id=2 @@ -99,6 +108,7 @@ EXAMPLES This gives an example of default output for all supported BTF kinds. **$ cat prog.c** + :: struct fwd_struct; @@ -139,6 +149,7 @@ This gives an example of default output for all supported BTF kinds. } **$ bpftool btf dump file prog.o** + :: [1] PTR '(anon)' type_id=2 @@ -225,19 +236,33 @@ All the standard ways to specify map or program are supported: **# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) +| +| **# bpftool btf dump file /sys/kernel/btf/i2c_smbus** +| (or) +| **# I2C_SMBUS_ID=$(bpftool btf show -p | jq '.[] | select(.name=="i2c_smbus").id')** +| **# bpftool btf dump id ${I2C_SMBUS_ID} -B /sys/kernel/btf/vmlinux** + +:: + + [104848] STRUCT 'i2c_smbus_alert' size=40 vlen=2 + 'alert' type_id=393 bits_offset=0 + 'ara' type_id=56050 bits_offset=256 + [104849] STRUCT 'alert_data' size=12 vlen=3 + 'addr' type_id=16 bits_offset=0 + 'type' type_id=56053 bits_offset=32 + 'data' type_id=7 bits_offset=64 + [104850] PTR '(anon)' type_id=104848 + [104851] PTR '(anon)' type_id=104849 + [104852] FUNC 'i2c_register_spd' type_id=84745 linkage=static + [104853] FUNC 'smbalert_driver_init' type_id=1213 linkage=static + [104854] FUNC_PROTO '(anon)' ret_type_id=18 vlen=1 + 'ara' type_id=56050 + [104855] FUNC 'i2c_handle_smbus_alert' type_id=104854 linkage=static + [104856] FUNC 'smbalert_remove' type_id=104854 linkage=static + [104857] FUNC_PROTO '(anon)' ret_type_id=18 vlen=2 + 'ara' type_id=56050 + 'id' type_id=56056 + [104858] FUNC 'smbalert_probe' type_id=104857 linkage=static + [104859] FUNC 'smbalert_work' type_id=9695 linkage=static + [104860] FUNC 'smbus_alert' type_id=71367 linkage=static + [104861] FUNC 'smbus_do_alert' type_id=84827 linkage=static diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index a226aee3574f..2ce900f66d6e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-cgroup ================ @@ -7,12 +9,14 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **cgroup** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } } *COMMANDS* := { **show** | **list** | **tree** | **attach** | **detach** | **help** } @@ -27,10 +31,20 @@ CGROUP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | -| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** } +| *ATTACH_TYPE* := { **cgroup_inet_ingress** | **cgroup_inet_egress** | +| **cgroup_inet_sock_create** | **cgroup_sock_ops** | +| **cgroup_device** | **cgroup_inet4_bind** | **cgroup_inet6_bind** | +| **cgroup_inet4_post_bind** | **cgroup_inet6_post_bind** | +| **cgroup_inet4_connect** | **cgroup_inet6_connect** | +| **cgroup_unix_connect** | **cgroup_inet4_getpeername** | +| **cgroup_inet6_getpeername** | **cgroup_unix_getpeername** | +| **cgroup_inet4_getsockname** | **cgroup_inet6_getsockname** | +| **cgroup_unix_getsockname** | **cgroup_udp4_sendmsg** | +| **cgroup_udp6_sendmsg** | **cgroup_unix_sendmsg** | +| **cgroup_udp4_recvmsg** | **cgroup_udp6_recvmsg** | +| **cgroup_unix_recvmsg** | **cgroup_sysctl** | +| **cgroup_getsockopt** | **cgroup_setsockopt** | +| **cgroup_inet_sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -91,21 +105,29 @@ DESCRIPTION **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); + **connect_unix** call to connect(2) for a unix socket (since 6.7); **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); + **sendmsg_unix** call to sendto(2), sendmsg(2), sendmmsg(2) for + an unconnected unix socket (since 6.7); **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for - an unconnected udp4 socket (since 5.2); + an unconnected udp4 socket (since 5.2); **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for - an unconnected udp6 socket (since 5.2); + an unconnected udp6 socket (since 5.2); + **recvmsg_unix** call to recvfrom(2), recvmsg(2), recvmmsg(2) for + an unconnected unix socket (since 6.7); **sysctl** sysctl access (since 5.2); **getsockopt** call to getsockopt (since 5.3); **setsockopt** call to setsockopt (since 5.3); **getpeername4** call to getpeername(2) for an inet4 socket (since 5.8); **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); + **getpeername_unix** call to getpeername(2) for a unix socket (since 6.7); **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **getsockname_unix** call to getsockname(2) for a unix socket (since 6.7); + **sock_release** closing an userspace inet socket (since 5.9). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type @@ -116,26 +138,11 @@ DESCRIPTION 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**. + .. include:: common_options.rst -f, --bpffs Show file names of pinned programs. - -d, --debug - Print all logs available from libbpf, including debug-level - information. - EXAMPLES ======== | @@ -158,19 +165,3 @@ EXAMPLES :: ID AttachType AttachFlags Name - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 8609f06e71de..e44039f89be7 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + =============== bpftool-feature =============== @@ -7,12 +9,14 @@ tool for inspection of eBPF-related parameters for Linux kernel or net device :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **feature** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **probe** | **help** } @@ -20,9 +24,11 @@ FEATURE COMMANDS ================ | **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature list_builtins** *GROUP* | **bpftool** **feature help** | | *COMPONENT* := { **kernel** | **dev** *NAME* } +| *GROUP* := { **prog_types** | **map_types** | **attach_types** | **link_types** | **helpers** } DESCRIPTION =========== @@ -66,40 +72,19 @@ DESCRIPTION The keywords **full**, **macros** and **prefix** have the same role as when probing the kernel. + **bpftool feature list_builtins** *GROUP* + List items known to bpftool. These can be BPF program types + (**prog_types**), BPF map types (**map_types**), attach types + (**attach_types**), link types (**link_types**), or BPF helper + functions (**helpers**). The command does not probe the system, but + simply lists the elements that bpftool knows from compilation time, + as provided from libbpf (for all object types) or from the BPF UAPI + header (list of helpers). This can be used in scripts to iterate over + BPF types or helpers. + **bpftool feature help** Print short help message. OPTIONS ======= - -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. - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) + .. include:: common_options.rst diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index df85dbd962c0..5e60825818dd 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-gen ================ @@ -7,23 +9,48 @@ tool for BPF code-generation :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **gen** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } } - *COMMAND* := { **skeleton** | **help** } + *COMMAND* := { **object** | **skeleton** | **help** } GEN COMMANDS ============= -| **bpftool** **gen skeleton** *FILE* +| **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] +| **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] | **bpftool** **gen help** DESCRIPTION =========== + **bpftool gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] + Statically link (combine) together one or more *INPUT_FILE*'s + into a single resulting *OUTPUT_FILE*. All the files involved + are BPF ELF object files. + + The rules of BPF static linking are mostly the same as for + user-space object files, but in addition to combining data + and instruction sections, .BTF and .BTF.ext (if present in + any of the input files) data are combined together. .BTF + data is deduplicated, so all the common types across + *INPUT_FILE*'s will only be represented once in the resulting + BTF information. + + BPF static linking allows to partition BPF source code into + individually compiled files that are then linked into + a single resulting BPF object file, which can be used to + generated BPF skeleton (with **gen skeleton** command) or + passed directly into **libbpf** (using **bpf_object__open()** + family of APIs). + **bpftool gen skeleton** *FILE* Generate BPF skeleton C header file for a given *FILE*. @@ -75,10 +102,13 @@ DESCRIPTION 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: + Each of them is prefixed with object name. Object name can + either be derived from object file name, i.e., if BPF object + file name is **example.o**, BPF object name will be + **example**. Object name can be also specified explicitly + through **name** *OBJECT_NAME* parameter. The following + custom functions are provided (assuming **example** as + the object name): - **example__open** and **example__open_opts**. These functions are used to instantiate skeleton. It @@ -121,49 +151,78 @@ DESCRIPTION (non-read-only) data from userspace, with same simplicity as for BPF side. + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given + *INPUT* BTF file, containing all needed BTF types so one, or + more, given eBPF objects CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, + libbpf, when loading an eBPF object, has to rely on external + BTF files to be able to calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel + DWARF data using pahole. It contains all the types used by + its respective kernel image and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized + to one or multiple eBPF objects, so they can be distributed + together with an eBPF CO-RE based application, turning the + application portable to different kernel versions. + + Check examples bellow for more information how to use it. + **bpftool gen help** Print short help message. OPTIONS ======= - -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. + .. include:: common_options.rst - -p, --pretty - Generate human-readable JSON output. Implies **-j**. - - -d, --debug - Print all logs available from libbpf, including debug-level - information. + -L, --use-loader + For skeletons, generate a "light" skeleton (also known as "loader" + skeleton). A light skeleton contains a loader eBPF program. It does + not use the majority of the libbpf infrastructure, and does not need + libelf. EXAMPLES ======== -**$ cat example.c** +**$ cat example1.bpf.c** + :: #include <stdbool.h> #include <linux/ptrace.h> #include <linux/bpf.h> - #include "bpf_helpers.h" + #include <bpf/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) { @@ -175,6 +234,21 @@ EXAMPLES return 0; } +**$ cat example2.bpf.c** + +:: + + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + SEC("raw_tp/sys_exit") int handle_sys_exit(struct pt_regs *ctx) { @@ -183,10 +257,51 @@ EXAMPLES return 0; } -This is example BPF application with two BPF programs and a mix of BPF maps -and global variables. +**$ cat example3.bpf.c** + +:: + + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + /* This header file is provided by the bpf_testmod module. */ + #include "bpf_testmod.h" + + int test_2_result = 0; + + /* bpf_Testmod.ko calls this function, passing a "4" + * and testmod_map->data. + */ + SEC("struct_ops/test_2") + void BPF_PROG(test_2, int a, int b) + { + test_2_result = a + b; + } + + SEC(".struct_ops") + struct bpf_testmod_ops testmod_map = { + .test_2 = (void *)test_2, + .data = 0x1, + }; + +This is example BPF application with three BPF programs and a mix of BPF +maps and global variables. Source code is split across three source code +files. + +**$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o** + +**$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o** + +**$ clang --target=bpf -g example3.bpf.c -o example3.bpf.o** + +**$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o example3.bpf.o** + +This set of commands compiles *example1.bpf.c*, *example2.bpf.c* and +*example3.bpf.c* individually and then statically links respective object +files into the final BPF ELF object file *example.bpf.o*. + +**$ bpftool gen skeleton example.bpf.o name example | tee example.skel.h** -**$ bpftool gen skeleton example.o** :: /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ @@ -206,7 +321,15 @@ and global variables. struct bpf_map *data; struct bpf_map *bss; struct bpf_map *my_map; + struct bpf_map *testmod_map; } maps; + struct { + struct example__testmod_map__bpf_testmod_ops { + const struct bpf_program *test_1; + const struct bpf_program *test_2; + int data; + } *testmod_map; + } struct_ops; struct { struct bpf_program *handle_sys_enter; struct bpf_program *handle_sys_exit; @@ -219,6 +342,7 @@ and global variables. struct { int x; } data; + int test_2_result; } *bss; struct example__data { _Bool global_flag; @@ -240,7 +364,8 @@ and global variables. #endif /* __EXAMPLE_SKEL_H__ */ -**$ cat example_user.c** +**$ cat example.c** + :: #include "example.skel.h" @@ -256,10 +381,16 @@ and global variables. skel->rodata->param1 = 128; + /* Change the value through the pointer of shadow type */ + skel->struct_ops.testmod_map->data = 13; + err = example__load(skel); if (err) goto cleanup; + /* The result of the function test_2() */ + printf("test_2_result: %d\n", skel->bss->test_2_result); + err = example__attach(skel); if (err) goto cleanup; @@ -282,27 +413,80 @@ and global variables. return err; } -**# ./example_user** +**# ./example** + :: + test_2_result: 17 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-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst index 8dce698eab79..84839d488621 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-iter.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ============ bpftool-iter ============ @@ -7,24 +9,29 @@ tool to create BPF iterators :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **iter** *COMMAND* + *OPTIONS* := { |COMMON_OPTIONS| } + *COMMANDS* := { **pin** | **help** } ITER COMMANDS =================== -| **bpftool** **iter pin** *OBJ* *PATH* +| **bpftool** **iter pin** *OBJ* *PATH* [**map** *MAP*] | **bpftool** **iter help** | | *OBJ* := /a/file/of/bpf_iter_target.o +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } DESCRIPTION =========== - **bpftool iter pin** *OBJ* *PATH* + **bpftool iter pin** *OBJ* *PATH* [**map** *MAP*] A bpf iterator combines a kernel iterating of particular kernel data (e.g., tasks, bpf_maps, etc.) and a bpf program called for each kernel data object @@ -37,6 +44,12 @@ DESCRIPTION character ('.'), which is reserved for future extensions of *bpffs*. + Map element bpf iterator requires an additional parameter + *MAP* so bpf program can iterate over map elements for + that map. User can have a bpf program in kernel to run + with each map element, do checking, filtering, aggregation, + etc. without copying data to user space. + User can then *cat PATH* to see the bpf iterator output. **bpftool iter help** @@ -44,16 +57,7 @@ DESCRIPTION OPTIONS ======= - -h, --help - Print short generic help message (similar to **bpftool help**). - - -V, --version - Print version number (similar to **bpftool version**). - - -d, --debug - Print all logs available, even debug-level information. This - includes logs from libbpf as well as from the verifier, when - attempting to load programs. + .. include:: common_options.rst EXAMPLES ======== @@ -64,18 +68,9 @@ EXAMPLES Create a file-based bpf iterator from bpf_iter_netlink.o and pin it to /sys/fs/bpf/my_netlink -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) +**# bpftool iter pin bpf_iter_hashmap.o /sys/fs/bpf/my_hashmap map id 20** + +:: + + Create a file-based bpf iterator from bpf_iter_hashmap.o and map with + id 20, and pin it to /sys/fs/bpf/my_hashmap diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst index 0e43d7b06c11..52a4eee4af54 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-link.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-link ================ @@ -7,12 +9,14 @@ tool for inspection and simple manipulation of eBPF links :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **link** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := { **show** | **list** | **pin** | **help** } @@ -21,6 +25,7 @@ LINK COMMANDS | **bpftool** **link { show | list }** [*LINK*] | **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link detach** *LINK* | **bpftool** **link help** | | *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } @@ -37,6 +42,11 @@ DESCRIPTION zero or more named attributes, some of which depend on type of link. + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + links. On such kernels bpftool will automatically emit this + information as well. + **bpftool link pin** *LINK* *FILE* Pin link *LINK* as *FILE*. @@ -44,23 +54,19 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. + **bpftool link detach** *LINK* + Force-detach link *LINK*. BPF link and its underlying BPF + program will stay valid, but they will be detached from the + respective BPF hook and BPF link will transition into + a defunct state until last open file descriptor for that + link is closed. + **bpftool link help** Print short help message. OPTIONS ======= - -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**. + .. include:: common_options.rst -f, --bpffs When showing BPF links, show file names of pinned @@ -70,10 +76,6 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. - -d, --debug - Print all logs available, even debug-level information. This - includes logs from libbpf. - EXAMPLES ======== **# bpftool link show** @@ -82,6 +84,7 @@ EXAMPLES 10: cgroup prog 25 cgroup_id 614 attach_type egress + pids test_progs(223) **# bpftool --json --pretty link show** @@ -91,7 +94,12 @@ EXAMPLES "type": "cgroup", "prog_id": 25, "cgroup_id": 614, - "attach_type": "egress" + "attach_type": "egress", + "pids": [{ + "pid": 223, + "comm": "test_progs" + } + ] } ] @@ -102,20 +110,3 @@ EXAMPLES :: -rw------- 1 root root 0 Apr 23 21:39 link - - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 70c78faa47ab..9d6a314dfd7a 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-map ================ @@ -7,23 +9,26 @@ tool for inspection and simple manipulation of eBPF maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **map** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := - { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** - | **delete** | **pin** | **help** } + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | + **delete** | **pin** | **help** } MAP COMMANDS ============= | **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ -| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] +| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ +| [**offload_dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* [**key** *DATA*] @@ -49,7 +54,8 @@ MAP COMMANDS | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** -| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** } +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** +| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** | **arena** } DESCRIPTION =========== @@ -62,7 +68,12 @@ DESCRIPTION Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). - **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + maps. On such kernels bpftool will automatically emit this + information as well. + + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**offload_dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -70,8 +81,13 @@ DESCRIPTION desired flags, e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h UAPI header for existing flags). - Keyword **dev** expects a network interface name, and is used - to request hardware offload for the map. + To create maps of type array-of-maps or hash-of-maps, the + **inner_map** keyword must be used to pass an inner map. The + kernel needs it to collect metadata related to the inner maps + that the new map will work with. + + Keyword **offload_dev** expects a network interface name, + and is used to request hardware offload for the map. **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, @@ -150,18 +166,7 @@ DESCRIPTION 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**. + .. include:: common_options.rst -f, --bpffs Show file names of pinned maps. @@ -170,17 +175,15 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. - -d, --debug - Print all logs available from libbpf, including debug-level - information. - EXAMPLES ======== **# bpftool map show** + :: 10: hash name some_map flags 0x0 - key 4B value 8B max_entries 2048 memlock 167936B + key 4B value 8B max_entries 2048 memlock 167936B + pids systemd(1) The following three commands are equivalent: @@ -197,6 +200,7 @@ The following three commands are equivalent: **# bpftool map dump id 10** + :: key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 @@ -204,6 +208,7 @@ The following three commands are equivalent: Found 2 elements **# bpftool map getnext id 10 key 0 1 2 3** + :: key: @@ -270,19 +275,3 @@ would be lost as soon as bpftool exits). key: 00 00 00 00 value: 22 02 00 00 Found 1 element - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index aa7450736179..dd3f9469765b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -1,18 +1,22 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-net ================ ------------------------------------------------------------------------------- -tool for inspection of netdev/tc related bpf prog attachments +tool for inspection of networking related bpf prog attachments ------------------------------------------------------------------------------- :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **net** *COMMAND* - *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } @@ -31,66 +35,55 @@ NET COMMANDS DESCRIPTION =========== **bpftool net { show | list }** [ **dev** *NAME* ] - List bpf program attachments in the kernel networking subsystem. - - Currently, only device driver xdp attachments and tc filter - classification/action attachments are implemented, i.e., for - program types **BPF_PROG_TYPE_SCHED_CLS**, - **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. - For programs attached to a particular cgroup, e.g., - **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, - **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, - users can use **bpftool cgroup** to dump cgroup attachments. - For sk_{filter, skb, msg, reuseport} and lwt/seg6 - bpf programs, users should consult other tools, e.g., iproute2. - - The current output will start with all xdp program attachments, followed by - all tc class/qdisc bpf program attachments. Both xdp programs and - tc programs are ordered based on ifindex number. If multiple bpf - programs attached to the same networking device through **tc filter**, - the order will be first all bpf programs attached to tc classes, then - all bpf programs attached to non clsact qdiscs, and finally all - bpf programs attached to root and clsact qdisc. + List bpf program attachments in the kernel networking subsystem. + + Currently, device driver xdp attachments, tcx, netkit and old-style tc + classifier/action attachments, flow_dissector as well as netfilter + attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT**, **BPF_PROG_TYPE_FLOW_DISSECTOR**, + **BPF_PROG_TYPE_NETFILTER**. + + For programs attached to a particular cgroup, e.g., + **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, + **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + users can use **bpftool cgroup** to dump cgroup attachments. + For sk_{filter, skb, msg, reuseport} and lwt/seg6 + bpf programs, users should consult other tools, e.g., iproute2. + + The current output will start with all xdp program attachments, followed by + all tcx, netkit, then tc class/qdisc bpf program attachments, then flow_dissector + and finally netfilter programs. Both xdp programs and tcx/netkit/tc programs are + ordered based on ifindex number. If multiple bpf programs attached + to the same networking device through **tc**, the order will be first + all bpf programs attached to tcx, netkit, then tc classes, then all bpf programs + attached to non clsact qdiscs, and finally all bpf programs attached + to root and clsact qdisc. **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] - Attach bpf program *PROG* to network interface *NAME* with - type specified by *ATTACH_TYPE*. Previously attached bpf program - can be replaced by the command used with **overwrite** option. - Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + Attach bpf program *PROG* to network interface *NAME* with + type specified by *ATTACH_TYPE*. Previously attached bpf program + can be replaced by the command used with **overwrite** option. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. - *ATTACH_TYPE* can be of: - **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; - **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; - **xdpdrv** - Native XDP. runs earliest point in driver's receive path; - **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; + *ATTACH_TYPE* can be of: + **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; + **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; + **xdpdrv** - Native XDP. runs earliest point in driver's receive path; + **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* - Detach bpf program attached to network interface *NAME* with - type specified by *ATTACH_TYPE*. To detach bpf program, same - *ATTACH_TYPE* previously used for attach must be specified. - Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + Detach bpf program attached to network interface *NAME* with + type specified by *ATTACH_TYPE*. To detach bpf program, same + *ATTACH_TYPE* previously used for attach must be specified. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. **bpftool net help** Print short help message. OPTIONS ======= - -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. + .. include:: common_options.rst EXAMPLES ======== @@ -187,20 +180,3 @@ EXAMPLES :: xdp: - - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index 9c592b7c6775..5fea633a82f1 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-perf ================ @@ -7,12 +9,14 @@ tool for inspection of perf related bpf prog attachments :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **perf** *COMMAND* - *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **help** } @@ -40,22 +44,7 @@ DESCRIPTION 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. + .. include:: common_options.rst EXAMPLES ======== @@ -78,20 +67,3 @@ EXAMPLES {"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 -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 2b254959d488..58e6a5b10ef7 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-prog ================ @@ -7,25 +9,29 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **prog** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | + { **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | + { **-L** | **--use-loader** } } *COMMANDS* := - { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** - | **loadall** | **help** } + { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | + **loadall** | **help** } PROG COMMANDS ============= | **bpftool** **prog** { **show** | **list** } [*PROG*] -| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] -| **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] +| **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] +| **bpftool** **prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -41,17 +47,21 @@ PROG COMMANDS | **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** | | **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | -| **cgroup/connect4** | **cgroup/connect6** | **cgroup/getpeername4** | **cgroup/getpeername6** | -| **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | -| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | -| **cgroup/getsockopt** | **cgroup/setsockopt** | -| **struct_ops** | **fentry** | **fexit** | **freplace** +| **cgroup/connect4** | **cgroup/connect6** | **cgroup/connect_unix** | +| **cgroup/getpeername4** | **cgroup/getpeername6** | **cgroup/getpeername_unix** | +| **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/getsockname_unix** | +| **cgroup/sendmsg4** | **cgroup/sendmsg6** | **cgroup/sendmsg_unix** | +| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/recvmsg_unix** | **cgroup/sysctl** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | +| **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } -| *ATTACH_TYPE* := { -| **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** +| *ATTACH_TYPE* := { +| **sk_msg_verdict** | **sk_skb_verdict** | **sk_skb_stream_verdict** | +| **sk_skb_stream_parser** | **flow_dissector** | } | *METRICs* := { -| **cycles** | **instructions** | **l1d_loads** | **llc_misses** +| **cycles** | **instructions** | **l1d_loads** | **llc_misses** | +| **itlb_misses** | **dtlb_misses** | } @@ -75,7 +85,12 @@ DESCRIPTION program run. Activation or deactivation of the feature is performed via the **kernel.bpf_stats_enabled** sysctl knob. - **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + programs. On such kernels bpftool will automatically emit this + information as well. + + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] 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** @@ -93,11 +108,10 @@ DESCRIPTION CFG in DOT format, on standard output. If the programs have line_info available, the source line will - be displayed by default. If **linum** is specified, - the filename, line number and line column will also be - displayed on top of the source line. + be displayed. If **linum** is specified, the filename, line + number and line column will also be displayed. - **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] + **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, @@ -107,9 +121,8 @@ DESCRIPTION **opcodes** controls if raw opcodes will be printed. If the prog has line_info available, the source line will - be displayed by default. If **linum** is specified, - the filename, line number and line column will also be - displayed on top of the source line. + be displayed. If **linum** is specified, the filename, line + number and line column will also be displayed. **bpftool prog pin** *PROG* *FILE* Pin program *PROG* as *FILE*. @@ -118,7 +131,7 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog loadall** pins all programs @@ -132,11 +145,25 @@ DESCRIPTION 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). + If **offload_dev** *NAME* is specified program will be loaded + onto given networking device (offload). + If **xdpmeta_dev** *NAME* is specified program will become + device-bound without offloading, this facilitates access + to XDP metadata. Optional **pinmaps** argument can be provided to pin all maps under *MAP_DIR* directory. + If **autoattach** is specified program will be attached + before pin. In that case, only the link (representing the + program attached to its hook) is pinned, not the program as + such, so the path won't show in **bpftool prog show -f**, + only show in **bpftool link show -f**. Also, this only works + when bpftool (libbpf) is able to infer all necessary + information from the object file, in particular, it's not + supported for all program types. If a program does not + support autoattach, bpftool falls back to regular pinning + for that program instead. + Note: *PATH* must be located in *bpffs* mount. It must not contain a dot character ('.'), which is reserved for future extensions of *bpffs*. @@ -205,18 +232,7 @@ DESCRIPTION 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**. + .. include:: common_options.rst -f, --bpffs When showing BPF programs, show file names of pinned @@ -229,10 +245,19 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. - -d, --debug - Print all logs available, even debug-level information. This - includes logs from libbpf as well as from the verifier, when - attempting to load programs. + -L, --use-loader + Load program as a "loader" program. This is useful to debug + the generation of such programs. When this option is in + use, bpftool attempts to load the programs from the object + file into the kernel, but does not pin them (therefore, the + *PATH* must not be provided). + + When combined with the **-d**\ \|\ **--debug** option, + additional debug messages are generated, and the execution + of the loader program will use the **bpf_trace_printk**\ () + helper to log each step of loading BTF, creating the maps, + and loading the programs (see **bpftool prog tracelog** as + a way to dump those messages). EXAMPLES ======== @@ -243,6 +268,7 @@ EXAMPLES 10: xdp name some_prog tag 005a3d2123620c8b gpl run_time_ns 81632 run_cnt 10 loaded_at 2017-09-29T20:11:00+0000 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 + pids systemd(1) **# bpftool --json --pretty prog show** @@ -262,6 +288,11 @@ EXAMPLES "bytes_jited": 370, "bytes_memlock": 4096, "map_ids": [10 + ], + "pids": [{ + "pid": 1, + "comm": "systemd" + } ] } ] @@ -332,18 +363,15 @@ EXAMPLES 42518139 instructions # 1.06 insns per cycle (83.39%) 123 llc_misses # 2.89 LLC misses per million insns (83.15%) -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-struct_ops**\ (8) +| +| Output below is for the trace logs. +| Run in separate terminals: +| **# bpftool prog tracelog** +| **# bpftool prog load -L -d file.o** + +:: + + bpftool-620059 [004] d... 2634685.517903: bpf_trace_printk: btf_load size 665 r=5 + bpftool-620059 [004] d... 2634685.517912: bpf_trace_printk: map_create sample_map idx 0 type 2 value_size 4 value_btf_id 0 r=6 + bpftool-620059 [004] d... 2634685.517997: bpf_trace_printk: prog_load sample insn_cnt 13 r=7 + bpftool-620059 [004] d... 2634685.517999: bpf_trace_printk: close(5) = 0 diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst index d93cd1cb8b0f..8022b5321dbe 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================== bpftool-struct_ops ================== @@ -7,12 +9,14 @@ tool to register/unregister/introspect BPF struct_ops :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **struct_ops** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } @@ -22,7 +26,7 @@ STRUCT_OPS COMMANDS | **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*] | **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*] -| **bpftool** **struct_ops register** *OBJ* +| **bpftool** **struct_ops register** *OBJ* [*LINK_DIR*] | **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP* | **bpftool** **struct_ops help** | @@ -47,10 +51,14 @@ DESCRIPTION for the given struct_ops. Otherwise, it dumps all struct_ops currently existing in the system. - **bpftool struct_ops register** *OBJ* + **bpftool struct_ops register** *OBJ* [*LINK_DIR*] Register bpf struct_ops from *OBJ*. All struct_ops under - the ELF section ".struct_ops" will be registered to - its kernel subsystem. + the ELF section ".struct_ops" and ".struct_ops.link" will + be registered to its kernel subsystem. For each + struct_ops in the ".struct_ops.link" section, a link + will be created. You can give *LINK_DIR* to provide a + directory path where these links will be pinned with the + same name as their corresponding map name. **bpftool struct_ops unregister** *STRUCT_OPS_MAP* Unregister the *STRUCT_OPS_MAP* from the kernel subsystem. @@ -60,23 +68,7 @@ DESCRIPTION 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, even debug-level information. This - includes logs from libbpf as well as from the verifier, when - attempting to load programs. + .. include:: common_options.rst EXAMPLES ======== @@ -98,20 +90,3 @@ EXAMPLES :: Registered tcp_congestion_ops cubic id 110 - - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool**\ (8), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 420d4d5df8b6..09e4f2ff5658 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ BPFTOOL ================ @@ -7,6 +9,8 @@ tool for inspection and simple manipulation of eBPF programs and maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== @@ -16,17 +20,19 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } + *OBJECT* := { **map** | **prog** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } - *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } - | { **-j** | **--json** } [{ **-p** | **--pretty** }] } + *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } *MAP-COMMANDS* := - { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** - | **delete** | **pin** | **event_pipe** | **help** } + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | + **delete** | **pin** | **event_pipe** | **help** } - *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** - | **load** | **attach** | **detach** | **help** } + *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | + **load** | **attach** | **detach** | **help** } + + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } @@ -36,6 +42,14 @@ SYNOPSIS *FEATURE-COMMANDS* := { **probe** | **help** } + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects @@ -46,18 +60,7 @@ DESCRIPTION OPTIONS ======= - -h, --help - Print short 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**. + .. include:: common_options.rst -m, --mapcompat Allow loading maps with unknown map definitions. @@ -65,24 +68,3 @@ OPTIONS -n, --nomount Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. - - -d, --debug - Print all logs available, even debug-level information. This - includes logs from libbpf as well as from the verifier, when - attempting to load programs. - -SEE ALSO -======== - **bpf**\ (2), - **bpf-helpers**\ (7), - **bpftool-btf**\ (8), - **bpftool-cgroup**\ (8), - **bpftool-feature**\ (8), - **bpftool-gen**\ (8), - **bpftool-iter**\ (8), - **bpftool-link**\ (8), - **bpftool-map**\ (8), - **bpftool-net**\ (8), - **bpftool-perf**\ (8), - **bpftool-prog**\ (8), - **bpftool-struct_ops**\ (8) diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst new file mode 100644 index 000000000000..30df7a707f02 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -0,0 +1,25 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +-h, --help + Print short help message (similar to **bpftool help**). + +-V, --version + Print bpftool's version number (similar to **bpftool version**), the + number of the libbpf version in use, and optional features that were + included when bpftool was compiled. Optional features include linking + against LLVM or libbfd to provide the disassembler for JIT-ted + programs (**bpftool prog dump jited**) and usage of BPF skeletons + (some features like **bpftool prog profile** or showing pids + associated to BPF objects may rely on it). + +-j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + +-p, --pretty + Generate human-readable JSON output. Implies **-j**. + +-d, --debug + Print all logs available, even debug-level information. This includes + logs from libbpf as well as from the verifier, when attempting to + load programs. diff --git a/tools/bpf/bpftool/Documentation/substitutions.rst b/tools/bpf/bpftool/Documentation/substitutions.rst new file mode 100644 index 000000000000..827e3ffb1766 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/substitutions.rst @@ -0,0 +1,3 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +.. |COMMON_OPTIONS| replace:: { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 9e85f101be85..e9154ace80ff 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -1,6 +1,5 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) include ../../scripts/Makefile.include -include ../../scripts/utilities.mak ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(CURDIR))) @@ -14,40 +13,75 @@ else Q = @ endif -BPF_DIR = $(srctree)/tools/lib/bpf/ +BPF_DIR = $(srctree)/tools/lib/bpf ifneq ($(OUTPUT),) - LIBBPF_OUTPUT = $(OUTPUT)/libbpf/ - LIBBPF_PATH = $(LIBBPF_OUTPUT) + _OUTPUT := $(OUTPUT) else - LIBBPF_PATH = $(BPF_DIR) + _OUTPUT := $(CURDIR)/ endif - -LIBBPF = $(LIBBPF_PATH)libbpf.a - -BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) - -$(LIBBPF): FORCE - $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT)) - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a - -$(LIBBPF)-clean: +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ + +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include +LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf +LIBBPF := $(LIBBPF_OUTPUT)libbpf.a + +LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ +LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include +LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf +LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a + +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) + +$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): + $(QUIET_MKDIR)mkdir -p $@ + +$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ + DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers + +$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $< + +$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" $@ install_headers + +$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $< + +$(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT) $(call QUIET_CLEAN, libbpf) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) clean >/dev/null +$(LIBBPF_BOOTSTRAP)-clean: FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT) + $(call QUIET_CLEAN, libbpf-bootstrap) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) clean >/dev/null + prefix ?= /usr/local bash_compdir ?= /usr/share/bash-completion/completions CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers -CFLAGS += $(filter-out -Wswitch-enum,$(EXTRA_WARNINGS)) +CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(or $(OUTPUT),.) \ + -I$(LIBBPF_INCLUDE) \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ - -I$(srctree)/tools/include/uapi \ - -I$(srctree)/tools/lib \ - -I$(srctree)/tools/perf + -I$(srctree)/tools/include/uapi +ifneq ($(BPFTOOL_VERSION),) CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) endif @@ -57,13 +91,24 @@ endif INSTALL ?= install RM ?= rm -f -CLANG ?= clang FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ - clang-bpf-global-var -FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ - clang-bpf-global-var + +FEATURE_TESTS := clang-bpf-co-re +FEATURE_TESTS += llvm +FEATURE_TESTS += libcap +FEATURE_TESTS += libbfd +FEATURE_TESTS += libbfd-liberty +FEATURE_TESTS += libbfd-liberty-z +FEATURE_TESTS += disassembler-four-args +FEATURE_TESTS += disassembler-init-styled + +FEATURE_DISPLAY := clang-bpf-co-re +FEATURE_DISPLAY += llvm +FEATURE_DISPLAY += libcap +FEATURE_DISPLAY += libbfd +FEATURE_DISPLAY += libbfd-liberty +FEATURE_DISPLAY += libbfd-liberty-z check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -81,15 +126,8 @@ include $(FEATURES_DUMP) endif endif -ifeq ($(feature-disassembler-four-args), 1) -CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE -endif - -ifeq ($(feature-reallocarray), 0) -CFLAGS += -DCOMPAT_NEED_REALLOCARRAY -endif - LIBS = $(LIBBPF) -lelf -lz +LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz ifeq ($(feature-libcap), 1) CFLAGS += -DUSE_LIBCAP LIBS += -lcap @@ -99,74 +137,137 @@ include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool -BFD_SRCS = jit_disasm.c +SRCS := $(wildcard *.c) + +ifeq ($(feature-llvm),1) + # If LLVM is available, use it for JIT disassembly + CFLAGS += -DHAVE_LLVM_SUPPORT + LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets + CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static) + LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LIBS += -lstdc++ + endif + LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags) +else + # Fall back on libbfd + ifeq ($(feature-libbfd),1) + LIBS += -lbfd -ldl -lopcodes + else ifeq ($(feature-libbfd-liberty),1) + LIBS += -lbfd -ldl -lopcodes -liberty + else ifeq ($(feature-libbfd-liberty-z),1) + LIBS += -lbfd -ldl -lopcodes -liberty -lz + endif + + # If one of the above feature combinations is set, we support libbfd + ifneq ($(filter -lbfd,$(LIBS)),) + CFLAGS += -DHAVE_LIBBFD_SUPPORT + + # Libbfd interface changed over time, figure out what we need + ifeq ($(feature-disassembler-four-args), 1) + CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE + endif + ifeq ($(feature-disassembler-init-styled), 1) + CFLAGS += -DDISASM_INIT_STYLED + endif + endif +endif +ifeq ($(filter -DHAVE_LLVM_SUPPORT -DHAVE_LIBBFD_SUPPORT,$(CFLAGS)),) + # No support for JIT disassembly + SRCS := $(filter-out jit_disasm.c,$(SRCS)) +endif -SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c)) +HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ + $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) -ifeq ($(feature-libbfd),1) - LIBS += -lbfd -ldl -lopcodes -else ifeq ($(feature-libbfd-liberty),1) - LIBS += -lbfd -ldl -lopcodes -liberty -else ifeq ($(feature-libbfd-liberty-z),1) - LIBS += -lbfd -ldl -lopcodes -liberty -lz -endif +BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool -ifneq ($(filter -lbfd,$(LIBS)),) -CFLAGS += -DHAVE_LIBBFD_SUPPORT -SRCS += $(BFD_SRCS) -endif +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o -_OBJS = $(filter-out $(OUTPUT)prog.o,$(OBJS)) $(OUTPUT)_prog.o +$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS) -ifeq ($(feature-clang-bpf-global-var),1) - __OBJS = $(OBJS) -else - __OBJS = $(_OBJS) -endif +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) + +bootstrap: $(BPFTOOL_BOOTSTRAP) -$(OUTPUT)_prog.o: prog.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -DBPFTOOL_WITHOUT_SKELETONS -o $@ $< +ifneq ($(VMLINUX_BTF)$(VMLINUX_H),) +ifeq ($(feature-clang-bpf-co-re),1) -$(OUTPUT)_bpftool: $(_OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(_OBJS) $(LIBS) +BUILD_BPF_SKELS := 1 + +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) +ifeq ($(VMLINUX_H),) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ +else + $(Q)cp "$(VMLINUX_H)" $@ +endif -skeleton/profiler.bpf.o: skeleton/profiler.bpf.c $(LIBBPF) +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ + -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ - -I$(LIBBPF_PATH) -I$(srctree)/tools/lib \ - -g -O2 -target bpf -c $< -o $@ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ + -g -O2 -Wall -fno-stack-protector \ + --target=bpf -c $< -o $@ + $(Q)$(LLVM_STRIP) -g $@ + +$(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@ + +$(OUTPUT)prog.o: $(OUTPUT)profiler.skel.h + +$(OUTPUT)pids.o: $(OUTPUT)pid_iter.skel.h -profiler.skel.h: $(OUTPUT)_bpftool skeleton/profiler.bpf.o - $(QUIET_GEN)$(OUTPUT)./_bpftool gen skeleton skeleton/profiler.bpf.o > $@ +endif +endif -$(OUTPUT)prog.o: prog.c profiler.skel.h - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< +CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) + +$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + +$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) + $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ -$(OUTPUT)feature.o: | zdep +$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@ -$(OUTPUT)bpftool: $(__OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(__OBJS) $(LIBS) +$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ $(OUTPUT)%.o: %.c - $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ -clean: $(LIBBPF)-clean +feature-detect-clean: + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + +clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean $(call QUIET_CLEAN, bpftool) $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d - $(Q)$(RM) -- $(OUTPUT)_bpftool profiler.skel.h skeleton/profiler.bpf.o - $(Q)$(RM) -r -- $(OUTPUT)libbpf/ + $(Q)$(RM) -- $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h + $(Q)$(RM) -r -- $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(call QUIET_CLEAN, core-gen) $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool $(Q)$(RM) -r -- $(OUTPUT)feature/ -install: $(OUTPUT)bpftool +install-bin: $(OUTPUT)bpftool $(call QUIET_INSTALL, bpftool) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin $(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool + +install: install-bin $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir) $(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir) @@ -189,9 +290,10 @@ doc-uninstall: FORCE: -zdep: - @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi - -.PHONY: all FORCE clean install uninstall zdep +.SECONDARY: +.PHONY: all FORCE bootstrap clean install-bin install uninstall .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all + +# Delete partially updated (corrupted) files on error +.DELETE_ON_ERROR: diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 25b25aca1112..6e4f7ce6bc01 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -255,30 +255,34 @@ _bpftool_map_update_get_name() _bpftool() { - local cur prev words objword + local cur prev words objword json=0 _init_completion || return # Deal with options if [[ ${words[cword]} == -* ]]; then - local c='--version --json --pretty --bpffs --mapcompat --debug' + local c='--version --json --pretty --bpffs --mapcompat --debug \ + --use-loader --base-btf' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi + if _bpftool_search_list -j --json -p --pretty; then + json=1 + fi # Deal with simplest keywords case $prev in - help|hex|opcodes|visual|linum) + help|hex) return 0 ;; tag) _bpftool_get_prog_tags return 0 ;; - dev) + dev|offload_dev|xdpmeta_dev) _sysfs_get_netdevs return 0 ;; - file|pinned) + file|pinned|-B|--base-btf) _filedir return 0 ;; @@ -291,7 +295,8 @@ _bpftool() # 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 + if [[ ${words[i]::1} == - ]] && + [[ ${words[i]} != "-B" ]] && [[ ${words[i]} != "--base-btf" ]]; then words=( "${words[@]:0:i}" "${words[@]:i+1}" ) [[ $i -le $cword ]] && cword=$(( cword - 1 )) else @@ -343,7 +348,8 @@ _bpftool() local PROG_TYPE='id pinned tag name' local MAP_TYPE='id pinned name' - local METRIC_TYPE='cycles instructions l1d_loads llc_misses' + local METRIC_TYPE='cycles instructions l1d_loads llc_misses \ + itlb_misses dtlb_misses' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -363,13 +369,16 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) + # "file" is not compatible with other keywords here + if _bpftool_search_list 'file'; then + return 0 + fi + if ! _bpftool_search_list 'linum opcodes visual'; then + _bpftool_once_attr 'file' + fi + _bpftool_once_attr 'linum opcodes' + if _bpftool_search_list 'xlated' && [[ "$json" == 0 ]]; then + _bpftool_once_attr 'visual' fi return 0 ;; @@ -404,8 +413,10 @@ _bpftool() return 0 ;; 5) - COMPREPLY=( $( compgen -W 'msg_verdict stream_verdict \ - stream_parser flow_dissector' -- "$cur" ) ) + local BPFTOOL_PROG_ATTACH_TYPES='sk_msg_verdict \ + sk_skb_verdict sk_skb_stream_verdict sk_skb_stream_parser \ + flow_dissector' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_ATTACH_TYPES" -- "$cur" ) ) return 0 ;; 6) @@ -464,23 +475,23 @@ _bpftool() case $prev in type) - COMPREPLY=( $( compgen -W "socket kprobe \ + local BPFTOOL_PROG_LOAD_TYPES='socket kprobe \ kretprobe classifier flow_dissector \ action tracepoint raw_tracepoint \ xdp perf_event cgroup/skb cgroup/sock \ cgroup/dev lwt_in lwt_out lwt_xmit \ - lwt_seg6local sockops sk_skb sk_msg \ - lirc_mode2 cgroup/bind4 cgroup/bind6 \ - cgroup/connect4 cgroup/connect6 \ - cgroup/getpeername4 cgroup/getpeername6 \ - cgroup/getsockname4 cgroup/getsockname6 \ - cgroup/sendmsg4 cgroup/sendmsg6 \ - cgroup/recvmsg4 cgroup/recvmsg6 \ + lwt_seg6local sockops sk_skb sk_msg lirc_mode2 \ + cgroup/bind4 cgroup/bind6 \ + cgroup/connect4 cgroup/connect6 cgroup/connect_unix \ + cgroup/getpeername4 cgroup/getpeername6 cgroup/getpeername_unix \ + cgroup/getsockname4 cgroup/getsockname6 cgroup/getsockname_unix \ + cgroup/sendmsg4 cgroup/sendmsg6 cgroup/sendmsg_unix \ + cgroup/recvmsg4 cgroup/recvmsg6 cgroup/recvmsg_unix \ cgroup/post_bind4 cgroup/post_bind6 \ cgroup/sysctl cgroup/getsockopt \ - cgroup/setsockopt struct_ops \ - fentry fexit freplace" -- \ - "$cur" ) ) + cgroup/setsockopt cgroup/sock_release struct_ops \ + fentry fexit freplace sk_lookup' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_LOAD_TYPES" -- "$cur" ) ) return 0 ;; id) @@ -497,9 +508,8 @@ _bpftool() ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) - _bpftool_once_attr 'type' - _bpftool_once_attr 'dev' - _bpftool_once_attr 'pinmaps' + _bpftool_once_attr 'type pinmaps autoattach' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' return 0 ;; esac @@ -615,7 +625,23 @@ _bpftool() iter) case $command in pin) - _filedir + case $prev in + $command) + _filedir + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + *) + _bpftool_one_of_list $MAP_TYPE + ;; + esac return 0 ;; *) @@ -682,27 +708,36 @@ _bpftool() return 0 ;; type) - COMPREPLY=( $( compgen -W 'hash array prog_array \ - perf_event_array percpu_hash percpu_array \ - stack_trace cgroup_array lru_hash \ - lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap devmap_hash sockmap cpumap \ - xskmap sockhash cgroup_storage reuseport_sockarray \ - percpu_cgroup_storage queue stack' -- \ - "$cur" ) ) + local BPFTOOL_MAP_CREATE_TYPES="$(bpftool feature list_builtins map_types 2>/dev/null | \ + grep -v '^unspec$')" + COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) return 0 ;; - key|value|flags|name|entries) + key|value|flags|entries) return 0 ;; + inner_map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + ;; + name) + case $pprev in + inner_map) + _bpftool_get_map_names + ;; + *) + return 0 + ;; + esac + ;; *) - _bpftool_once_attr 'type' - _bpftool_once_attr 'key' - _bpftool_once_attr 'value' - _bpftool_once_attr 'entries' - _bpftool_once_attr 'name' - _bpftool_once_attr 'flags' - _bpftool_once_attr 'dev' + _bpftool_once_attr 'type key value entries name flags offload_dev' + if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then + _bpftool_once_attr 'inner_map' + fi return 0 ;; esac @@ -843,8 +878,7 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'cpu' - _bpftool_once_attr 'index' + _bpftool_once_attr 'cpu index' return 0 ;; esac @@ -944,12 +978,41 @@ _bpftool() ;; gen) case $command in + object) + _filedir + return 0 + ;; skeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) _filedir + return 0 ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) ;; esac ;; @@ -967,34 +1030,33 @@ _bpftool() return 0 ;; attach|detach) - local ATTACH_TYPES='ingress egress sock_create sock_ops \ - device bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ - getpeername4 getpeername6 getsockname4 getsockname6 \ - sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt' + local BPFTOOL_CGROUP_ATTACH_TYPES="$(bpftool feature list_builtins attach_types 2>/dev/null | \ + grep '^cgroup_')" local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' - case $prev in - $command) - _filedir - return 0 - ;; - ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ - post_bind4|post_bind6|connect4|connect6|getpeername4|\ - getpeername6|getsockname4|getsockname6|sendmsg4|sendmsg6|\ - recvmsg4|recvmsg6|sysctl|getsockopt|setsockopt) + # Check for $prev = $command first + if [ $prev = $command ]; then + _filedir + return 0 + # Then check for attach type. This is done outside of the + # "case $prev in" to avoid writing the whole list of attach + # types again as pattern to match (where we cannot reuse + # our variable). + elif [[ $BPFTOOL_CGROUP_ATTACH_TYPES =~ $prev ]]; then COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 - ;; + fi + # case/esac for the other cases + case $prev in id) _bpftool_get_prog_ids return 0 ;; *) - if ! _bpftool_search_list "$ATTACH_TYPES"; then - COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- \ - "$cur" ) ) + if ! _bpftool_search_list "$BPFTOOL_CGROUP_ATTACH_TYPES"; then + COMPREPLY=( $( compgen -W \ + "$BPFTOOL_CGROUP_ATTACH_TYPES" -- "$cur" ) ) elif [[ "$command" == "attach" ]]; then # We have an attach type on the command line, # but it is not the previous word, or @@ -1098,15 +1160,20 @@ _bpftool() _bpftool_once_attr 'full unprivileged' return 0 ;; + list_builtins) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'prog_types map_types \ + attach_types link_types helpers' -- "$cur" ) ) + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'help probe' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'help list_builtins probe' -- "$cur" ) ) ;; esac ;; link) case $command in - show|list|pin) + show|list|pin|detach) case $prev in id) _bpftool_get_link_ids @@ -1123,7 +1190,7 @@ _bpftool() COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) return 0 ;; - pin) + pin|detach) if [[ $prev == "$command" ]]; then COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) else diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index faac8189b285..91fcb75babe3 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -8,14 +8,15 @@ #include <stdio.h> #include <string.h> #include <unistd.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 <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> + #include "json_writer.h" #include "main.h" @@ -36,16 +37,10 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", -}; - -struct btf_attach_table { - DECLARE_HASHTABLE(table, 16); -}; - -struct btf_attach_point { - __u32 obj_id; - __u32 btf_id; - struct hlist_node hash; + [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", }; static const char *btf_int_enc_str(__u8 encoding) @@ -70,7 +65,9 @@ static const char *btf_var_linkage_str(__u32 linkage) case BTF_VAR_STATIC: return "static"; case BTF_VAR_GLOBAL_ALLOCATED: - return "global-alloc"; + return "global"; + case BTF_VAR_GLOBAL_EXTERN: + return "extern"; default: return "(unknown)"; } @@ -97,26 +94,28 @@ static const char *btf_str(const struct btf *btf, __u32 off) return btf__name_by_offset(btf, off) ? : "(invalid)"; } +static int btf_kind_safe(int kind) +{ + return kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; +} + static int dump_btf_type(const struct btf *btf, __u32 id, const struct btf_type *t) { json_writer_t *w = json_wtr; - int kind, safe_kind; - - kind = BTF_INFO_KIND(t->info); - safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; + int kind = btf_kind(t); if (json_output) { jsonw_start_object(w); jsonw_uint_field(w, "id", id); - jsonw_string_field(w, "kind", btf_kind_str[safe_kind]); + jsonw_string_field(w, "kind", btf_kind_str[btf_kind_safe(kind)]); jsonw_string_field(w, "name", btf_str(btf, t->name_off)); } else { - printf("[%u] %s '%s'", id, btf_kind_str[safe_kind], + printf("[%u] %s '%s'", id, btf_kind_str[btf_kind_safe(kind)], btf_str(btf, t->name_off)); } - switch (BTF_INFO_KIND(t->info)) { + switch (kind) { case BTF_KIND_INT: { __u32 v = *(__u32 *)(t + 1); const char *enc; @@ -140,6 +139,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id, case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: if (json_output) jsonw_uint_field(w, "type_id", t->type); else @@ -208,15 +208,18 @@ static int dump_btf_type(const struct btf *btf, __u32 id, case BTF_KIND_ENUM: { const struct btf_enum *v = (const void *)(t + 1); __u16 vlen = BTF_INFO_VLEN(t->info); + const char *encoding; int i; + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; if (json_output) { + jsonw_string_field(w, "encoding", encoding); jsonw_uint_field(w, "size", t->size); jsonw_uint_field(w, "vlen", vlen); jsonw_name(w, "values"); jsonw_start_array(w); } else { - printf(" size=%u vlen=%u", t->size, vlen); + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); } for (i = 0; i < vlen; i++, v++) { const char *name = btf_str(btf, v->name_off); @@ -224,10 +227,57 @@ static int dump_btf_type(const struct btf *btf, __u32 id, if (json_output) { jsonw_start_object(w); jsonw_string_field(w, "name", name); - jsonw_uint_field(w, "val", v->val); + if (btf_kflag(t)) + jsonw_int_field(w, "val", v->val); + else + jsonw_uint_field(w, "val", v->val); jsonw_end_object(w); } else { - printf("\n\t'%s' val=%u", name, v->val); + if (btf_kflag(t)) + printf("\n\t'%s' val=%d", name, v->val); + else + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *v = btf_enum64(t); + __u16 vlen = btf_vlen(t); + const char *encoding; + int i; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + __u64 val = ((__u64)v->val_hi32 << 32) | v->val_lo32; + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + if (btf_kflag(t)) + jsonw_int_field(w, "val", val); + else + jsonw_uint_field(w, "val", val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%lldLL", name, + (unsigned long long)val); + else + printf("\n\t'%s' val=%lluULL", name, + (unsigned long long)val); } } if (json_output) @@ -299,7 +349,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id, break; } case BTF_KIND_DATASEC: { - const struct btf_var_secinfo *v = (const void *)(t+1); + const struct btf_var_secinfo *v = (const void *)(t + 1); + const struct btf_type *vt; __u16 vlen = BTF_INFO_VLEN(t->info); int i; @@ -321,12 +372,37 @@ static int dump_btf_type(const struct btf *btf, __u32 id, } else { printf("\n\ttype_id=%u offset=%u size=%u", v->type, v->offset, v->size); + + if (v->type < btf__type_cnt(btf)) { + vt = btf__type_by_id(btf, v->type); + printf(" (%s '%s')", + btf_kind_str[btf_kind_safe(btf_kind(vt))], + btf_str(btf, vt->name_off)); + } } } if (json_output) jsonw_end_array(w); break; } + case BTF_KIND_FLOAT: { + if (json_output) + jsonw_uint_field(w, "size", t->size); + else + printf(" size=%u", t->size); + break; + } + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + break; + } default: break; } @@ -357,9 +433,15 @@ static int dump_btf_raw(const struct btf *btf, dump_btf_type(btf, root_type_ids[i], t); } } else { - int cnt = btf__get_nr_types(btf); + const struct btf *base; + int cnt = btf__type_cnt(btf); + int start_id = 1; - for (i = 1; i <= cnt; i++) { + base = btf__base_btf(btf); + if (base) + start_id = btf__type_cnt(base); + + for (i = start_id; i < cnt; i++) { t = btf__type_by_id(btf, i); dump_btf_type(btf, i, t); } @@ -384,9 +466,9 @@ static int dump_btf_c(const struct btf *btf, struct btf_dump *d; int err = 0, i; - d = btf_dump__new(btf, NULL, NULL, btf_dump_printf); - if (IS_ERR(d)) - return PTR_ERR(d); + d = btf_dump__new(btf, btf_dump_printf, NULL, NULL); + if (!d) + return -errno; printf("#ifndef __VMLINUX_H__\n"); printf("#define __VMLINUX_H__\n"); @@ -402,9 +484,9 @@ static int dump_btf_c(const struct btf *btf, goto done; } } else { - int cnt = btf__get_nr_types(btf); + int cnt = btf__type_cnt(btf); - for (i = 1; i <= cnt; i++) { + for (i = 1; i < cnt; i++) { err = btf_dump__dump_type(d, i); if (err) goto done; @@ -422,71 +504,65 @@ done: return err; } -static struct btf *btf__parse_raw(const char *file) -{ - struct btf *btf; - struct stat st; - __u8 *buf; - FILE *f; - - if (stat(file, &st)) - return NULL; - - f = fopen(file, "rb"); - if (!f) - return NULL; - - buf = malloc(st.st_size); - if (!buf) { - btf = ERR_PTR(-ENOMEM); - goto exit_close; - } +static const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; - if ((size_t) st.st_size != fread(buf, 1, st.st_size, f)) { - btf = ERR_PTR(-EINVAL); - goto exit_free; - } +static struct btf *get_vmlinux_btf_from_sysfs(void) +{ + struct btf *base; - btf = btf__new(buf, st.st_size); + base = btf__parse(sysfs_vmlinux, NULL); + if (!base) + p_err("failed to parse vmlinux BTF at '%s': %d\n", + sysfs_vmlinux, -errno); -exit_free: - free(buf); -exit_close: - fclose(f); - return btf; + return base; } -static bool is_btf_raw(const char *file) +#define BTF_NAME_BUFF_LEN 64 + +static bool btf_is_kernel_module(__u32 btf_id) { - __u16 magic = 0; - int fd, nb_read; + struct bpf_btf_info btf_info = {}; + char btf_name[BTF_NAME_BUFF_LEN]; + int btf_fd; + __u32 len; + int err; - fd = open(file, O_RDONLY); - if (fd < 0) + btf_fd = bpf_btf_get_fd_by_id(btf_id); + if (btf_fd < 0) { + p_err("can't get BTF object by id (%u): %s", btf_id, strerror(errno)); return false; + } - nb_read = read(fd, &magic, sizeof(magic)); - close(fd); - return nb_read == sizeof(magic) && magic == BTF_MAGIC; + len = sizeof(btf_info); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); + close(btf_fd); + if (err) { + p_err("can't get BTF (ID %u) object info: %s", btf_id, strerror(errno)); + return false; + } + + return btf_info.kernel_btf && strncmp(btf_name, "vmlinux", sizeof(btf_name)) != 0; } static int do_dump(int argc, char **argv) { - struct btf *btf = NULL; + struct btf *btf = NULL, *base = NULL; __u32 root_type_ids[2]; int root_type_cnt = 0; bool dump_c = false; __u32 btf_id = -1; const char *src; int fd = -1; - int err; + int err = 0; if (!REQ_ARGS(2)) { usage(); return -1; } src = GET_ARG(); - if (is_prefix(src, "map")) { struct bpf_map_info info = {}; __u32 len = sizeof(info); @@ -530,7 +606,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) return -1; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info: %s", strerror(errno)); goto done; @@ -547,16 +623,18 @@ static int do_dump(int argc, char **argv) } NEXT_ARG(); } else if (is_prefix(src, "file")) { - if (is_btf_raw(*argv)) - btf = btf__parse_raw(*argv); - else - btf = btf__parse_elf(*argv, NULL); + const char sysfs_prefix[] = "/sys/kernel/btf/"; + + if (!base_btf && + strncmp(*argv, sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0 && + strcmp(*argv, sysfs_vmlinux) != 0) + base = get_vmlinux_btf_from_sysfs(); - if (IS_ERR(btf)) { - err = -PTR_ERR(btf); - btf = NULL; + btf = btf__parse_split(*argv, base ?: base_btf); + if (!btf) { + err = -errno; p_err("failed to load BTF from %s: %s", - *argv, strerror(err)); + *argv, strerror(errno)); goto done; } NEXT_ARG(); @@ -571,6 +649,7 @@ static int do_dump(int argc, char **argv) NEXT_ARG(); if (argc < 1) { p_err("expecting value for 'format' option\n"); + err = -EINVAL; goto done; } if (strcmp(*argv, "c") == 0) { @@ -580,24 +659,28 @@ static int do_dump(int argc, char **argv) } else { p_err("unrecognized format specifier: '%s', possible values: raw, c", *argv); + err = -EINVAL; goto done; } NEXT_ARG(); } else { p_err("unrecognized option: '%s'", *argv); + err = -EINVAL; goto done; } } if (!btf) { - err = btf__get_from_id(btf_id, &btf); - if (err) { - p_err("get btf by id (%u): %s", btf_id, strerror(err)); - goto done; + if (!base_btf && btf_is_kernel_module(btf_id)) { + p_info("Warning: valid base BTF was not specified with -B option, falling back to standard base BTF (%s)", + sysfs_vmlinux); + base_btf = get_vmlinux_btf_from_sysfs(); } + + btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); if (!btf) { - err = ENOENT; - p_err("can't find btf with ID (%u)", btf_id); + err = -errno; + p_err("get btf by id (%u): %s", btf_id, strerror(errno)); goto done; } } @@ -616,6 +699,7 @@ static int do_dump(int argc, char **argv) done: close(fd); btf__free(btf); + btf__free(base); return err; } @@ -646,21 +730,8 @@ static int btf_parse_fd(int *argc, char ***argv) return fd; } -static void delete_btf_table(struct btf_attach_table *tab) -{ - struct btf_attach_point *obj; - struct hlist_node *tmp; - - unsigned int bkt; - - hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { - hash_del(&obj->hash); - free(obj); - } -} - static int -build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, +build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, void *info, __u32 *len) { static const char * const names[] = { @@ -668,7 +739,6 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, [BPF_OBJ_PROG] = "prog", [BPF_OBJ_MAP] = "map", }; - struct btf_attach_point *obj_node; __u32 btf_id, id = 0; int err; int fd; @@ -719,7 +789,10 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, } memset(info, 0, *len); - err = bpf_obj_get_info_by_fd(fd, info, len); + if (type == BPF_OBJ_PROG) + err = bpf_prog_get_info_by_fd(fd, info, len); + else + err = bpf_map_get_info_by_fd(fd, info, len); close(fd); if (err) { p_err("can't get %s info: %s", names[type], @@ -742,27 +815,24 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, if (!btf_id) continue; - obj_node = calloc(1, sizeof(*obj_node)); - if (!obj_node) { - p_err("failed to allocate memory: %s", strerror(errno)); + err = hashmap__append(tab, btf_id, id); + if (err) { + p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s", + btf_id, id, strerror(-err)); goto err_free; } - - obj_node->obj_id = id; - obj_node->btf_id = btf_id; - hash_add(tab->table, &obj_node->hash, obj_node->btf_id); } return 0; err_free: - delete_btf_table(tab); + hashmap__free(tab); return err; } static int -build_btf_tables(struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) +build_btf_tables(struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { struct bpf_prog_info prog_info; __u32 prog_len = sizeof(prog_info); @@ -778,7 +848,7 @@ build_btf_tables(struct btf_attach_table *btf_prog_table, err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info, &map_len); if (err) { - delete_btf_table(btf_prog_table); + hashmap__free(btf_prog_table); return err; } @@ -787,38 +857,44 @@ build_btf_tables(struct btf_attach_table *btf_prog_table, static void show_btf_plain(struct bpf_btf_info *info, int fd, - struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { - struct btf_attach_point *obj; + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); int n; printf("%u: ", info->id); + if (info->kernel_btf) + printf("name [%s] ", name); + else if (name && name[0]) + printf("name %s ", name); + else + printf("name <anon> "); printf("size %uB", info->btf_size); n = 0; - hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) { - if (obj->btf_id == info->id) - printf("%s%u", n++ == 0 ? " prog_ids " : ",", - obj->obj_id); + hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " prog_ids " : ",", entry->value); } n = 0; - hash_for_each_possible(btf_map_table->table, obj, hash, info->id) { - if (obj->btf_id == info->id) - printf("%s%u", n++ == 0 ? " map_ids " : ",", - obj->obj_id); + hashmap__for_each_key_entry(btf_map_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " map_ids " : ",", entry->value); } + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + printf("\n"); } static void show_btf_json(struct bpf_btf_info *info, int fd, - struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { - struct btf_attach_point *obj; + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); jsonw_start_object(json_wtr); /* btf object */ jsonw_uint_field(json_wtr, "id", info->id); @@ -826,37 +902,56 @@ show_btf_json(struct bpf_btf_info *info, int fd, jsonw_name(json_wtr, "prog_ids"); jsonw_start_array(json_wtr); /* prog_ids */ - hash_for_each_possible(btf_prog_table->table, obj, hash, - info->id) { - if (obj->btf_id == info->id) - jsonw_uint(json_wtr, obj->obj_id); + hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { + jsonw_uint(json_wtr, entry->value); } jsonw_end_array(json_wtr); /* prog_ids */ jsonw_name(json_wtr, "map_ids"); jsonw_start_array(json_wtr); /* map_ids */ - hash_for_each_possible(btf_map_table->table, obj, hash, - info->id) { - if (obj->btf_id == info->id) - jsonw_uint(json_wtr, obj->obj_id); + hashmap__for_each_key_entry(btf_map_table, entry, info->id) { + jsonw_uint(json_wtr, entry->value); } jsonw_end_array(json_wtr); /* map_ids */ + + emit_obj_refs_json(refs_table, info->id, json_wtr); /* pids */ + + jsonw_bool_field(json_wtr, "kernel", info->kernel_btf); + + if (name && name[0]) + jsonw_string_field(json_wtr, "name", name); + jsonw_end_object(json_wtr); /* btf object */ } static int -show_btf(int fd, struct btf_attach_table *btf_prog_table, - struct btf_attach_table *btf_map_table) +show_btf(int fd, struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) { - struct bpf_btf_info info = {}; + struct bpf_btf_info info; __u32 len = sizeof(info); + char name[64]; int err; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + memset(&info, 0, sizeof(info)); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get BTF object info: %s", strerror(errno)); return -1; } + /* if kernel support emitting BTF object name, pass name pointer */ + if (info.name_len) { + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + err = bpf_btf_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get BTF object info: %s", strerror(errno)); + return -1; + } + } if (json_output) show_btf_json(&info, fd, btf_prog_table, btf_map_table); @@ -868,8 +963,8 @@ show_btf(int fd, struct btf_attach_table *btf_prog_table, static int do_show(int argc, char **argv) { - struct btf_attach_table btf_prog_table; - struct btf_attach_table btf_map_table; + struct hashmap *btf_prog_table; + struct hashmap *btf_map_table; int err, fd = -1; __u32 id = 0; @@ -885,17 +980,28 @@ static int do_show(int argc, char **argv) return BAD_ARG(); } - hash_init(btf_prog_table.table); - hash_init(btf_map_table.table); - err = build_btf_tables(&btf_prog_table, &btf_map_table); + btf_prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + btf_map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + if (fd >= 0) + close(fd); + p_err("failed to create hashmap for object references"); + return -1; + } + err = build_btf_tables(btf_prog_table, btf_map_table); if (err) { if (fd >= 0) close(fd); return err; } + build_obj_refs_table(&refs_table, BPF_OBJ_BTF); if (fd >= 0) { - err = show_btf(fd, &btf_prog_table, &btf_map_table); + err = show_btf(fd, btf_prog_table, btf_map_table); close(fd); goto exit_free; } @@ -927,7 +1033,7 @@ static int do_show(int argc, char **argv) break; } - err = show_btf(fd, &btf_prog_table, &btf_map_table); + err = show_btf(fd, btf_prog_table, btf_map_table); close(fd); if (err) break; @@ -937,8 +1043,9 @@ static int do_show(int argc, char **argv) jsonw_end_array(json_wtr); /* root array */ exit_free: - delete_btf_table(&btf_prog_table); - delete_btf_table(&btf_map_table); + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + delete_obj_refs_table(refs_table); return err; } @@ -959,7 +1066,8 @@ static int do_help(int argc, char **argv) " FORMAT := { raw | c }\n" " " HELP_SPEC_MAP "\n" " " HELP_SPEC_PROGRAM "\n" - " " HELP_SPEC_OPTIONS "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-B|--base-btf} }\n" "", bin_name, "btf"); diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index ede162f83eea..527fe867a8fb 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -32,14 +32,16 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, const struct btf_type *func_proto, __u32 prog_id) { - struct bpf_prog_info_linear *prog_info = NULL; const struct btf_type *func_type; + int prog_fd = -1, func_sig_len; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); const char *prog_name = NULL; - struct bpf_func_info *finfo; struct btf *prog_btf = NULL; - struct bpf_prog_info *info; - int prog_fd, func_sig_len; + struct bpf_func_info finfo; + __u32 finfo_rec_size; char prog_str[1024]; + int err; /* Get the ptr's func_proto */ func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0, @@ -52,23 +54,30 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, /* Get the bpf_prog's name. Obtain from func_info. */ prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (prog_fd == -1) + if (prog_fd < 0) goto print; - prog_info = bpf_program__get_prog_info_linear(prog_fd, - 1UL << BPF_PROG_INFO_FUNC_INFO); - close(prog_fd); - if (IS_ERR(prog_info)) { - prog_info = NULL; + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + if (!info.btf_id || !info.nr_func_info) goto print; - } - info = &prog_info->info; - if (!info->btf_id || !info->nr_func_info || - btf__get_from_id(info->btf_id, &prog_btf)) + finfo_rec_size = info.func_info_rec_size; + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = finfo_rec_size; + info.func_info = ptr_to_u64(&finfo); + + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) goto print; - finfo = (struct bpf_func_info *)info->func_info; - func_type = btf__type_by_id(prog_btf, finfo->type_id); + func_type = btf__type_by_id(prog_btf, finfo.type_id); if (!func_type || !btf_is_func(func_type)) goto print; @@ -90,7 +99,8 @@ print: prog_str[sizeof(prog_str) - 1] = '\0'; jsonw_string(d->jw, prog_str); btf__free(prog_btf); - free(prog_info); + if (prog_fd >= 0) + close(prog_fd); return 0; } @@ -117,7 +127,7 @@ static void btf_dumper_ptr(const struct btf_dumper *d, print_ptr_value: if (d->is_plain_text) - jsonw_printf(d->jw, "%p", (void *)value); + jsonw_printf(d->jw, "\"%p\"", (void *)value); else jsonw_printf(d->jw, "%lu", value); } @@ -172,6 +182,32 @@ static int btf_dumper_enum(const struct btf_dumper *d, return 0; } +static int btf_dumper_enum64(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum64 *enums = btf_enum64(t); + __u32 val_lo32, val_hi32; + __u64 value; + __u16 i; + + value = *(__u64 *)data; + val_lo32 = (__u32)value; + val_hi32 = value >> 32; + + for (i = 0; i < btf_vlen(t); i++) { + if (val_lo32 == enums[i].val_lo32 && val_hi32 == enums[i].val_hi32) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + static bool is_str_array(const struct btf *btf, const struct btf_array *arr, const char *s) { @@ -416,7 +452,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, *(char *)data); break; case BTF_INT_BOOL: - jsonw_bool(jw, *(int *)data); + jsonw_bool(jw, *(bool *)data); break; default: /* shouldn't happen */ @@ -532,6 +568,8 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, return btf_dumper_array(d, type_id, data); case BTF_KIND_ENUM: return btf_dumper_enum(d, t, data); + case BTF_KIND_ENUM64: + return btf_dumper_enum64(d, t, data); case BTF_KIND_PTR: btf_dumper_ptr(d, t, data); return 0; @@ -596,6 +634,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: case BTF_KIND_TYPEDEF: + case BTF_KIND_FLOAT: BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off)); break; case BTF_KIND_STRUCT: @@ -607,6 +646,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, btf__name_by_offset(btf, t->name_off)); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: BTF_PRINT_ARG("enum %s ", btf__name_by_offset(btf, t->name_off)); break; @@ -781,3 +821,86 @@ void btf_dump_linfo_json(const struct btf *btf, BPF_LINE_INFO_LINE_COL(linfo->line_col)); } } + +static void dotlabel_puts(const char *s) +{ + for (; *s; ++s) { + switch (*s) { + case '\\': + case '"': + case '{': + case '}': + case '<': + case '>': + case '|': + case ' ': + putchar('\\'); + fallthrough; + default: + putchar(*s); + } + } +} + +static const char *shorten_path(const char *path) +{ + const unsigned int MAX_PATH_LEN = 32; + size_t len = strlen(path); + const char *shortpath; + + if (len <= MAX_PATH_LEN) + return path; + + /* Search for last '/' under the MAX_PATH_LEN limit */ + shortpath = strchr(path + len - MAX_PATH_LEN, '/'); + if (shortpath) { + if (shortpath < path + strlen("...")) + /* We removed a very short prefix, e.g. "/w", and we'll + * make the path longer by prefixing with the ellipsis. + * Not worth it, keep initial path. + */ + return path; + return shortpath; + } + + /* File base name length is > MAX_PATH_LEN, search for last '/' */ + shortpath = strrchr(path, '/'); + if (shortpath) + return shortpath; + + return path; +} + +void btf_dump_linfo_dotlabel(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (!line || !strlen(line)) + return; + line = ltrim(line); + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + const char *shortfile; + + /* More forgiving on file because linum option is + * expected to provide more info than the already + * available src line. + */ + if (!file) + shortfile = ""; + else + shortfile = shorten_path(file); + + printf("; [%s", shortfile > file ? "..." : ""); + dotlabel_puts(shortfile); + printf(" line:%u col:%u]\\l\\\n", + BPF_LINE_INFO_LINE_NUM(linfo->line_col), + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } + + printf("; "); + dotlabel_puts(line); + printf("\\l\\\n"); +} diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c index 1951219a9af7..eec437cca2ea 100644 --- a/tools/bpf/bpftool/cfg.c +++ b/tools/bpf/bpftool/cfg.c @@ -380,7 +380,9 @@ static void cfg_destroy(struct cfg *cfg) } } -static void draw_bb_node(struct func_node *func, struct bb_node *bb) +static void +draw_bb_node(struct func_node *func, struct bb_node *bb, struct dump_data *dd, + bool opcodes, bool linum) { const char *shape; @@ -398,13 +400,10 @@ static void draw_bb_node(struct func_node *func, struct bb_node *bb) printf("EXIT"); } else { unsigned int start_idx; - struct dump_data dd = {}; - - printf("{"); - kernel_syms_load(&dd); + printf("{\\\n"); start_idx = bb->head - func->start; - dump_xlated_for_graph(&dd, bb->head, bb->tail, start_idx); - kernel_syms_destroy(&dd); + dump_xlated_for_graph(dd, bb->head, bb->tail, start_idx, + opcodes, linum); printf("}"); } @@ -430,12 +429,14 @@ static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb) } } -static void func_output_bb_def(struct func_node *func) +static void +func_output_bb_def(struct func_node *func, struct dump_data *dd, + bool opcodes, bool linum) { struct bb_node *bb; list_for_each_entry(bb, &func->bbs, l) { - draw_bb_node(func, bb); + draw_bb_node(func, bb, dd, opcodes, linum); } } @@ -455,7 +456,8 @@ static void func_output_edges(struct func_node *func) func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX); } -static void cfg_dump(struct cfg *cfg) +static void +cfg_dump(struct cfg *cfg, struct dump_data *dd, bool opcodes, bool linum) { struct func_node *func; @@ -463,14 +465,15 @@ static void cfg_dump(struct cfg *cfg) list_for_each_entry(func, &cfg->funcs, l) { printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n", func->idx, func->idx); - func_output_bb_def(func); + func_output_bb_def(func, dd, opcodes, linum); func_output_edges(func); printf("}\n"); } printf("}\n"); } -void dump_xlated_cfg(void *buf, unsigned int len) +void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) { struct bpf_insn *insn = buf; struct cfg cfg; @@ -479,7 +482,7 @@ void dump_xlated_cfg(void *buf, unsigned int len) if (cfg_build(&cfg, insn, len)) return; - cfg_dump(&cfg); + cfg_dump(&cfg, dd, opcodes, linum); cfg_destroy(&cfg); } diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h index e144257ea6d2..b3793f4e1783 100644 --- a/tools/bpf/bpftool/cfg.h +++ b/tools/bpf/bpftool/cfg.h @@ -4,6 +4,9 @@ #ifndef __BPF_TOOL_CFG_H #define __BPF_TOOL_CFG_H -void dump_xlated_cfg(void *buf, unsigned int len); +#include "xlated_dumper.h" + +void dump_xlated_cfg(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); #endif /* __BPF_TOOL_CFG_H */ diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index d901cc1b904a..af6898c0f388 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -15,41 +15,94 @@ #include <unistd.h> #include <bpf/bpf.h> +#include <bpf/btf.h> #include "main.h" #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ - " sock_ops | device | bind4 | bind6 |\n" \ - " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | getpeername4 | getpeername6 |\n" \ - " getsockname4 | getsockname6 | sendmsg4 |\n" \ - " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { cgroup_inet_ingress | cgroup_inet_egress |\n" \ + " cgroup_inet_sock_create | cgroup_sock_ops |\n" \ + " cgroup_device | cgroup_inet4_bind |\n" \ + " cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \ + " cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \ + " cgroup_inet6_connect | cgroup_unix_connect |\n" \ + " cgroup_inet4_getpeername | cgroup_inet6_getpeername |\n" \ + " cgroup_unix_getpeername | cgroup_inet4_getsockname |\n" \ + " cgroup_inet6_getsockname | cgroup_unix_getsockname |\n" \ + " cgroup_udp4_sendmsg | cgroup_udp6_sendmsg |\n" \ + " cgroup_unix_sendmsg | cgroup_udp4_recvmsg |\n" \ + " cgroup_udp6_recvmsg | cgroup_unix_recvmsg |\n" \ + " cgroup_sysctl | cgroup_getsockopt |\n" \ + " cgroup_setsockopt | cgroup_inet_sock_release }" static unsigned int query_flags; +static struct btf *btf_vmlinux; +static __u32 btf_vmlinux_id; static enum bpf_attach_type parse_attach_type(const char *str) { + const char *attach_type_str; enum bpf_attach_type type; - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - if (attach_type_name[type] && - is_prefix(str, attach_type_name[type])) + for (type = 0; ; type++) { + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!attach_type_str) + break; + if (!strcmp(str, attach_type_str)) + return type; + } + + /* Also check traditionally used attach type strings. For these we keep + * allowing prefixed usage. + */ + for (type = 0; ; type++) { + attach_type_str = bpf_attach_type_input_str(type); + if (!attach_type_str) + break; + if (is_prefix(str, attach_type_str)) return type; } return __MAX_BPF_ATTACH_TYPE; } +static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) +{ + struct bpf_btf_info btf_info = {}; + __u32 btf_len = sizeof(btf_info); + char name[16] = {}; + int err; + int fd; + + btf_info.name = ptr_to_u64(name); + btf_info.name_len = sizeof(name); + + fd = bpf_btf_get_fd_by_id(attach_btf_obj_id); + if (fd < 0) + return; + + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_len); + if (err) + goto out; + + if (btf_info.kernel_btf && strncmp(name, "vmlinux", sizeof(name)) == 0) + btf_vmlinux_id = btf_info.id; + +out: + close(fd); +} + static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { + char prog_name[MAX_PROG_FULL_NAME]; + const char *attach_btf_name = NULL; struct bpf_prog_info info = {}; + const char *attach_type_str; __u32 info_len = sizeof(info); int prog_fd; @@ -57,30 +110,58 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, if (prog_fd < 0) return -1; - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { close(prog_fd); return -1; } + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + + if (btf_vmlinux) { + if (!btf_vmlinux_id) + guess_vmlinux_btf_id(info.attach_btf_obj_id); + + if (btf_vmlinux_id == info.attach_btf_obj_id && + info.attach_btf_id < btf__type_cnt(btf_vmlinux)) { + const struct btf_type *t = + btf__type_by_id(btf_vmlinux, info.attach_btf_id); + attach_btf_name = + btf__name_by_offset(btf_vmlinux, t->name_off); + } + } + + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(json_wtr, "attach_type", - attach_type_name[attach_type]); + if (attach_type_str) + jsonw_string_field(json_wtr, "attach_type", attach_type_str); else jsonw_uint_field(json_wtr, "attach_type", attach_type); - jsonw_string_field(json_wtr, "attach_flags", - attach_flags_str); - jsonw_string_field(json_wtr, "name", info.name); + if (!(query_flags & BPF_F_QUERY_EFFECTIVE)) + jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); + jsonw_string_field(json_wtr, "name", prog_name); + if (attach_btf_name) + jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name); + jsonw_uint_field(json_wtr, "attach_btf_obj_id", info.attach_btf_obj_id); + jsonw_uint_field(json_wtr, "attach_btf_id", info.attach_btf_id); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("%-15s", attach_type_name[attach_type]); + if (attach_type_str) + printf("%-15s", attach_type_str); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, info.name); + if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf(" %-15s", prog_name); + else + printf(" %-15s %-15s", attach_flags_str, prog_name); + if (attach_btf_name) + printf(" %-15s", attach_btf_name); + else if (info.attach_btf_id) + printf(" attach_btf_obj_id=%d attach_btf_id=%d", + info.attach_btf_obj_id, info.attach_btf_id); + printf("\n"); } close(prog_fd); @@ -119,47 +200,90 @@ static int cgroup_has_attached_progs(int cgroup_fd) return no_prog ? 0 : 1; } + +static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_ids[1024] = {0}; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) + show_bpf_prog(prog_ids[iter], type, NULL, level); + + return 0; +} + static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_attach_flags[1024] = {0}; const char *attach_flags_str; __u32 prog_ids[1024] = {0}; - __u32 prog_cnt, iter; - __u32 attach_flags; char buf[32]; + __u32 iter; int ret; - prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, - prog_ids, &prog_cnt); + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + p.prog_attach_flags = prog_attach_flags; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); if (ret) return ret; - if (prog_cnt == 0) + if (p.prog_cnt == 0) return 0; - switch (attach_flags) { - case BPF_F_ALLOW_MULTI: - attach_flags_str = "multi"; - break; - case BPF_F_ALLOW_OVERRIDE: - attach_flags_str = "override"; - break; - case 0: - attach_flags_str = ""; - break; - default: - snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); - attach_flags_str = buf; - } + for (iter = 0; iter < p.prog_cnt; iter++) { + __u32 attach_flags; + + attach_flags = prog_attach_flags[iter] ?: p.attach_flags; + + switch (attach_flags) { + case BPF_F_ALLOW_MULTI: + attach_flags_str = "multi"; + break; + case BPF_F_ALLOW_OVERRIDE: + attach_flags_str = "override"; + break; + case 0: + attach_flags_str = ""; + break; + default: + snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); + attach_flags_str = buf; + } - for (iter = 0; iter < prog_cnt; iter++) show_bpf_prog(prog_ids[iter], type, attach_flags_str, level); + } return 0; } +static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + return query_flags & BPF_F_QUERY_EFFECTIVE ? + show_effective_bpf_progs(cgroup_fd, type, level) : + show_attached_bpf_progs(cgroup_fd, type, level); +} + static int do_show(int argc, char **argv) { enum bpf_attach_type type; @@ -207,10 +331,13 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name"); else printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType", "AttachFlags", "Name"); + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { /* * Not all attach types may be supported, so it's expected, @@ -218,7 +345,7 @@ 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) == 0) + if (show_bpf_progs(cgroup_fd, type, 0) == 0) ret = 0; } @@ -274,8 +401,9 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, printf("%s\n", fpath); } + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) - show_attached_bpf_progs(cgroup_fd, type, ftw->level); + show_bpf_progs(cgroup_fd, type, ftw->level); if (errno == EINVAL) /* Last attach type does not support query. @@ -349,6 +477,11 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%s\n" + "%-8s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "Name"); else printf("%s\n" "%-8s %-15s %-15s %-15s\n", @@ -500,7 +633,8 @@ static int do_help(int argc, char **argv) HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" - " " HELP_SPEC_OPTIONS "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} }\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index c47bdc65de8e..cc6e6aae2447 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif #include <ctype.h> #include <errno.h> #include <fcntl.h> -#include <fts.h> +#include <ftw.h> #include <libgen.h> #include <mntent.h> #include <stdbool.h> @@ -12,16 +15,21 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <linux/limits.h> -#include <linux/magic.h> #include <net/if.h> #include <sys/mount.h> #include <sys/resource.h> #include <sys/stat.h> #include <sys/vfs.h> +#include <linux/filter.h> +#include <linux/limits.h> +#include <linux/magic.h> +#include <linux/unistd.h> + #include <bpf/bpf.h> +#include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> #include "main.h" @@ -60,7 +68,7 @@ void p_info(const char *fmt, ...) va_end(ap); } -static bool is_bpffs(char *path) +static bool is_bpffs(const char *path) { struct statfs st_fs; @@ -70,11 +78,73 @@ static bool is_bpffs(char *path) return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; } +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and programs. This was done in + * commit 97306be45fbe ("Merge branch 'switch to memcg-based memory + * accounting'"), in Linux 5.11. + * + * Libbpf also offers to probe for memcg-based accounting vs rlimit, but does + * so by checking for the availability of a given BPF helper and this has + * failed on some kernels with backports in the past, see commit 6b4384ff1088 + * ("Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK""). + * Instead, we can probe by lowering the process-based rlimit to 0, trying to + * load a BPF object, and resetting the rlimit. If the load succeeds then + * memcg-based accounting is supported. + * + * This would be too dangerous to do in the library, because multithreaded + * applications might attempt to load items while the rlimit is at 0. Given + * that bpftool is single-threaded, this is fine to do here. + */ +static bool known_to_need_rlimit(void) +{ + struct rlimit rlim_init, rlim_cur_zero = {}; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd, err; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim_init)) + return false; + + /* Drop the soft limit to zero. We maintain the hard limit to its + * current value, because lowering it would be a permanent operation + * for unprivileged users. + */ + rlim_cur_zero.rlim_max = rlim_init.rlim_max; + if (setrlimit(RLIMIT_MEMLOCK, &rlim_cur_zero)) + return false; + + /* Do not use bpf_prog_load() from libbpf here, because it calls + * bump_rlimit_memlock(), interfering with the current probe. + */ + prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + err = errno; + + /* reset soft rlimit to its initial value */ + setrlimit(RLIMIT_MEMLOCK, &rlim_init); + + if (prog_fd < 0) + return err == EPERM; + + close(prog_fd); + return false; +} + void set_max_rlimit(void) { struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - setrlimit(RLIMIT_MEMLOCK, &rinf); + if (known_to_need_rlimit()) + setrlimit(RLIMIT_MEMLOCK, &rinf); } static int @@ -123,24 +193,35 @@ int mount_tracefs(const char *target) return err; } -int open_obj_pinned(char *path, bool quiet) +int open_obj_pinned(const char *path, bool quiet) { - int fd; + char *pname; + int fd = -1; - fd = bpf_obj_get(path); + pname = strdup(path); + if (!pname) { + if (!quiet) + p_err("mem alloc failed"); + goto out_ret; + } + + fd = bpf_obj_get(pname); if (fd < 0) { if (!quiet) - p_err("bpf obj get (%s): %s", path, - errno == EACCES && !is_bpffs(dirname(path)) ? + p_err("bpf obj get (%s): %s", pname, + errno == EACCES && !is_bpffs(dirname(pname)) ? "directory not in bpf file system (bpffs)" : strerror(errno)); - return -1; + goto out_free; } +out_free: + free(pname); +out_ret: return fd; } -int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) { enum bpf_obj_type type; int fd; @@ -163,14 +244,22 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name) +int mount_bpffs_for_pin(const char *name, bool is_dir) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; + if (is_dir && is_bpffs(name)) + return err; + file = malloc(strlen(name) + 1); + if (!file) { + p_err("mem alloc failed"); + return -1; + } + strcpy(file, name); dir = dirname(file); @@ -200,7 +289,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name); + err = mount_bpffs_for_pin(name, false); if (err) return err; @@ -216,6 +305,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; @@ -232,6 +324,7 @@ const char *get_fd_type_name(enum bpf_obj_type type) [BPF_OBJ_UNKNOWN] = "unknown", [BPF_OBJ_PROG] = "prog", [BPF_OBJ_MAP] = "map", + [BPF_OBJ_LINK] = "link", }; if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) @@ -240,6 +333,49 @@ const char *get_fd_type_name(enum bpf_obj_type type) return names[type]; } +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + int get_fd_type(int fd) { char path[PATH_MAX]; @@ -330,84 +466,95 @@ void print_hex_data_json(uint8_t *data, size_t len) jsonw_end_array(json_wtr); } -int build_pinned_obj_table(struct pinned_obj_table *tab, - enum bpf_obj_type type) +/* extra params for nftw cb */ +static struct hashmap *build_fn_table; +static enum bpf_obj_type build_fn_type; + +static int do_build_table_cb(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftwbuf) { - struct bpf_prog_info pinned_info = {}; - struct pinned_obj *obj_node = NULL; + struct bpf_prog_info pinned_info; __u32 len = sizeof(pinned_info); - struct mntent *mntent = NULL; enum bpf_obj_type objtype; + int fd, err = 0; + char *path; + + if (typeflag != FTW_F) + goto out_ret; + + fd = open_obj_pinned(fpath, true); + if (fd < 0) + goto out_ret; + + objtype = get_fd_type(fd); + if (objtype != build_fn_type) + goto out_close; + + memset(&pinned_info, 0, sizeof(pinned_info)); + if (bpf_prog_get_info_by_fd(fd, &pinned_info, &len)) + goto out_close; + + path = strdup(fpath); + if (!path) { + err = -1; + goto out_close; + } + + err = hashmap__append(build_fn_table, pinned_info.id, path); + if (err) { + p_err("failed to append entry to hashmap for ID %u, path '%s': %s", + pinned_info.id, path, strerror(errno)); + free(path); + goto out_close; + } + +out_close: + close(fd); +out_ret: + return err; +} + +int build_pinned_obj_table(struct hashmap *tab, + enum bpf_obj_type type) +{ + struct mntent *mntent = NULL; FILE *mntfile = NULL; - FTSENT *ftse = NULL; - FTS *fts = NULL; - int fd, err; + int flags = FTW_PHYS; + int nopenfd = 16; + int err = 0; mntfile = setmntent("/proc/mounts", "r"); if (!mntfile) return -1; + build_fn_table = tab; + build_fn_type = type; + while ((mntent = getmntent(mntfile))) { - char *path[] = { mntent->mnt_dir, NULL }; + char *path = mntent->mnt_dir; if (strncmp(mntent->mnt_type, "bpf", 3) != 0) continue; - - fts = fts_open(path, 0, NULL); - if (!fts) - continue; - - while ((ftse = fts_read(fts))) { - if (!(ftse->fts_info & FTS_F)) - continue; - fd = open_obj_pinned(ftse->fts_path, true); - if (fd < 0) - continue; - - objtype = get_fd_type(fd); - if (objtype != type) { - close(fd); - continue; - } - memset(&pinned_info, 0, sizeof(pinned_info)); - err = bpf_obj_get_info_by_fd(fd, &pinned_info, &len); - if (err) { - close(fd); - continue; - } - - obj_node = malloc(sizeof(*obj_node)); - if (!obj_node) { - close(fd); - fts_close(fts); - fclose(mntfile); - return -1; - } - - memset(obj_node, 0, sizeof(*obj_node)); - obj_node->id = pinned_info.id; - obj_node->path = strdup(ftse->fts_path); - hash_add(tab->table, &obj_node->hash, obj_node->id); - - close(fd); - } - fts_close(fts); + err = nftw(path, do_build_table_cb, nopenfd, flags); + if (err) + break; } fclose(mntfile); - return 0; + return err; } -void delete_pinned_obj_table(struct pinned_obj_table *tab) +void delete_pinned_obj_table(struct hashmap *map) { - struct pinned_obj *obj; - struct hlist_node *tmp; - unsigned int bkt; + struct hashmap_entry *entry; + size_t bkt; - hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { - hash_del(&obj->hash); - free(obj->path); - free(obj); - } + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) + free(entry->pvalue); + + hashmap__free(map); } unsigned int get_page_size(void) @@ -487,12 +634,11 @@ static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name) } const char * -ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, - const char **opt) +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt) { + __maybe_unused int device_id; char devname[IF_NAMESIZE]; int vendor_id; - int device_id; if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) { p_err("Can't get net device name for ifindex %d: %s", ifindex, @@ -507,6 +653,7 @@ ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, } switch (vendor_id) { +#ifdef HAVE_LIBBFD_SUPPORT case 0x19ee: device_id = read_sysfs_netdev_hex_int(devname, "device"); if (device_id != 0x4000 && @@ -515,8 +662,10 @@ ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch"); *opt = "ctx4"; return "NFP-6xxx"; +#endif /* HAVE_LIBBFD_SUPPORT */ + /* No NFP support in LLVM, we have no valid triple to return. */ default: - p_err("Can't get bfd arch name for device vendor id 0x%04x", + p_err("Can't get arch name for device vendor id 0x%04x", vendor_id); return NULL; } @@ -581,3 +730,381 @@ print_all_levels(__maybe_unused enum libbpf_print_level level, { return vfprintf(stderr, format, args); } + +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) +{ + char prog_name[MAX_PROG_FULL_NAME]; + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_prog_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) { + close(fd); + continue; + } + + if (!tag) { + get_prog_full_name(&info, fd, prog_name, + sizeof(prog_name)); + if (strncmp(nametag, prog_name, sizeof(prog_name))) { + close(fd); + continue; + } + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int prog_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "tag")) { + unsigned char tag[BPF_TAG_SIZE]; + + NEXT_ARGP(); + + if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, + tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) + != BPF_TAG_SIZE) { + p_err("can't parse tag"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(tag, fds, true); + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > MAX_PROG_FULL_NAME - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(name, fds, false); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int prog_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several programs match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +static int map_fd_by_name(char *name, int **fds) +{ + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_map_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int map_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_map_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get map by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return map_fd_by_name(name, fds); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int map_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several maps match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len) +{ + int err; + int fd; + + fd = map_parse_fd(argc, argv); + if (fd < 0) + return -1; + + err = bpf_map_get_info_by_fd(fd, info, info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return err; + } + + return fd; +} + +size_t hash_fn_for_key_as_id(long key, void *ctx) +{ + return key; +} + +bool equal_fn_for_key_as_id(long k1, long k2, void *ctx) +{ + return k1 == k2; +} + +const char *bpf_attach_type_input_str(enum bpf_attach_type t) +{ + switch (t) { + case BPF_CGROUP_INET_INGRESS: return "ingress"; + case BPF_CGROUP_INET_EGRESS: return "egress"; + case BPF_CGROUP_INET_SOCK_CREATE: return "sock_create"; + case BPF_CGROUP_INET_SOCK_RELEASE: return "sock_release"; + case BPF_CGROUP_SOCK_OPS: return "sock_ops"; + case BPF_CGROUP_DEVICE: return "device"; + case BPF_CGROUP_INET4_BIND: return "bind4"; + case BPF_CGROUP_INET6_BIND: return "bind6"; + case BPF_CGROUP_INET4_CONNECT: return "connect4"; + case BPF_CGROUP_INET6_CONNECT: return "connect6"; + case BPF_CGROUP_INET4_POST_BIND: return "post_bind4"; + case BPF_CGROUP_INET6_POST_BIND: return "post_bind6"; + case BPF_CGROUP_INET4_GETPEERNAME: return "getpeername4"; + case BPF_CGROUP_INET6_GETPEERNAME: return "getpeername6"; + case BPF_CGROUP_INET4_GETSOCKNAME: return "getsockname4"; + case BPF_CGROUP_INET6_GETSOCKNAME: return "getsockname6"; + case BPF_CGROUP_UDP4_SENDMSG: return "sendmsg4"; + case BPF_CGROUP_UDP6_SENDMSG: return "sendmsg6"; + case BPF_CGROUP_SYSCTL: return "sysctl"; + case BPF_CGROUP_UDP4_RECVMSG: return "recvmsg4"; + case BPF_CGROUP_UDP6_RECVMSG: return "recvmsg6"; + case BPF_CGROUP_GETSOCKOPT: return "getsockopt"; + case BPF_CGROUP_SETSOCKOPT: return "setsockopt"; + case BPF_TRACE_RAW_TP: return "raw_tp"; + case BPF_TRACE_FENTRY: return "fentry"; + case BPF_TRACE_FEXIT: return "fexit"; + case BPF_MODIFY_RETURN: return "mod_ret"; + case BPF_SK_REUSEPORT_SELECT: return "sk_skb_reuseport_select"; + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return "sk_skb_reuseport_select_or_migrate"; + default: return libbpf_bpf_attach_type_str(t); + } +} + +int pathname_concat(char *buf, int buf_sz, const char *path, + const char *name) +{ + int len; + + len = snprintf(buf, buf_sz, "%s/%s", path, name); + if (len < 0) + return -EINVAL; + if (len >= buf_sz) + return -ENAMETOOLONG; + + return 0; +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 768bf77df886..708733b0ea06 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -3,6 +3,7 @@ #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> #include <net/if.h> @@ -45,6 +46,11 @@ static bool run_as_unprivileged; /* Miscellaneous utility functions */ +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + static bool check_procfs(void) { struct statfs st_fs; @@ -135,12 +141,38 @@ static void print_end_section(void) /* Probing functions */ -static int read_procfs(const char *path) +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -162,7 +194,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -175,20 +207,23 @@ static void probe_unprivileged_disabled(void) printf("bpf() syscall for unprivileged users is enabled\n"); break; case 1: - printf("bpf() syscall restricted to privileged users\n"); + printf("bpf() syscall restricted to privileged users (without recovery)\n"); + break; + case 2: + printf("bpf() syscall restricted to privileged users (admin can change)\n"); break; case -1: printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -210,7 +245,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -218,7 +253,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -240,7 +275,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -248,7 +283,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -267,14 +302,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -287,7 +322,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } @@ -336,6 +371,10 @@ static void probe_kernel_image_config(const char *define_prefix) { "CONFIG_BPF_JIT", }, /* Avoid compiling eBPF interpreter (use JIT only) */ { "CONFIG_BPF_JIT_ALWAYS_ON", }, + /* Kernel BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF", }, + /* Kernel module BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF_MODULES", }, /* cgroups */ { "CONFIG_CGROUPS", }, @@ -387,10 +426,6 @@ static void probe_kernel_image_config(const char *define_prefix) { "CONFIG_BPF_STREAM_PARSER", }, /* xt_bpf module for passing BPF programs to netfilter */ { "CONFIG_NETFILTER_XT_MATCH_BPF", }, - /* bpfilter back-end for iptables */ - { "CONFIG_BPFILTER", }, - /* bpftilter module with "user mode helper" */ - { "CONFIG_BPFILTER_UMH", }, /* test_bpf module for BPF tests */ { "CONFIG_TEST_BPF", }, @@ -447,23 +482,23 @@ static void probe_kernel_image_config(const char *define_prefix) } } -end_parse: - if (file) - gzclose(file); - for (i = 0; i < ARRAY_SIZE(options); i++) { if (define_prefix && !options[i].macro_dump) continue; print_kernel_option(options[i].name, values[i], define_prefix); free(values[i]); } + +end_parse: + if (file) + gzclose(file); } static bool probe_bpf_syscall(const char *define_prefix) { bool res; - bpf_load_program(BPF_PROG_TYPE_UNSPEC, NULL, 0, NULL, 0, NULL, 0); + bpf_prog_load(BPF_PROG_TYPE_UNSPEC, NULL, NULL, NULL, 0, NULL); res = (errno != ENOSYS); print_bool_feature("have_bpf_syscall", @@ -474,17 +509,50 @@ static bool probe_bpf_syscall(const char *define_prefix) return res; } +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + static void -probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, - const char *define_prefix, __u32 ifindex) +probe_prog_type(enum bpf_prog_type prog_type, const char *prog_type_str, + bool *supported_types, const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF program_type "; size_t maxlen; bool res; - if (ifindex) - /* Only test offload-able program types */ + if (ifindex) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_XDP: @@ -493,7 +561,11 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, return; } - res = bpf_probe_prog_type(prog_type, ifindex); + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL) > 0; + } + #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -505,49 +577,108 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, supported_types[prog_type] |= res; maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(prog_type_name[prog_type]) > maxlen) { + if (strlen(prog_type_str) > maxlen) { p_info("program type name too long"); return; } - sprintf(feat_name, "have_%s_prog_type", prog_type_name[prog_type]); - sprintf(define_name, "%s_prog_type", prog_type_name[prog_type]); + sprintf(feat_name, "have_%s_prog_type", prog_type_str); + sprintf(define_name, "%s_prog_type", prog_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, prog_type_name[prog_type]); + sprintf(plain_desc, "%s%s", plain_comment, prog_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + static void -probe_map_type(enum bpf_map_type map_type, const char *define_prefix, - __u32 ifindex) +probe_map_type(enum bpf_map_type map_type, char const *map_type_str, + const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF map_type "; size_t maxlen; bool res; - res = bpf_probe_map_type(map_type, ifindex); + if (ifindex) { + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } + + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL) > 0; + } /* Probe result depends on the success of map creation, no additional * check required for unprivileged users */ maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(map_type_name[map_type]) > maxlen) { + if (strlen(map_type_str) > maxlen) { p_info("map type name too long"); return; } - sprintf(feat_name, "have_%s_map_type", map_type_name[map_type]); - sprintf(define_name, "%s_map_type", map_type_name[map_type]); + sprintf(feat_name, "have_%s_map_type", map_type_str); + sprintf(define_name, "%s_map_type", map_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, map_type_name[map_type]); + sprintf(plain_desc, "%s%s", plain_comment, map_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } -static void +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + +static bool probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, const char *ptype_name, __u32 ifindex) @@ -555,7 +686,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, bool res = false; if (supported_type) { - res = bpf_probe_helper(id, prog_type, ifindex); + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL) > 0; #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for * unprivileged users check that we did not fail because of @@ -577,15 +711,18 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, if (res) printf("\n\t- %s", helper_name[id]); } + + return res; } static void -probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, +probe_helpers_for_progtype(enum bpf_prog_type prog_type, + const char *prog_type_str, bool supported_type, const char *define_prefix, __u32 ifindex) { - const char *ptype_name = prog_type_name[prog_type]; char feat_name[128]; unsigned int id; + bool probe_res = false; if (ifindex) /* Only test helpers for offload-able program types */ @@ -598,12 +735,12 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, } if (json_output) { - sprintf(feat_name, "%s_available_helpers", ptype_name); + sprintf(feat_name, "%s_available_helpers", prog_type_str); jsonw_name(json_wtr, feat_name); jsonw_start_array(json_wtr); } else if (!define_prefix) { printf("eBPF helpers supported for program type %s:", - ptype_name); + prog_type_str); } for (id = 1; id < ARRAY_SIZE(helper_name); id++) { @@ -612,33 +749,139 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ switch (id) { case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: case BPF_FUNC_probe_write_user: if (!full_mode) continue; - /* fallthrough */ + fallthrough; default: - probe_helper_for_progtype(prog_type, supported_type, - define_prefix, id, ptype_name, + probe_res |= probe_helper_for_progtype(prog_type, supported_type, + define_prefix, id, prog_type_str, ifindex); } } if (json_output) jsonw_end_array(json_wtr); - else if (!define_prefix) + else if (!define_prefix) { printf("\n"); + if (!probe_res) { + if (!supported_type) + printf("\tProgram type not supported\n"); + else + printf("\tCould not determine which helpers are available\n"); + } + } + + } static void -probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +probe_misc_feature(struct bpf_insn *insns, size_t len, + const char *define_prefix, __u32 ifindex, + const char *feat_name, const char *plain_name, + const char *define_name) { + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_ifindex = ifindex, + ); bool res; + int fd; + + errno = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, len, &opts); + res = fd >= 0 || !errno; + + if (fd >= 0) + close(fd); + + print_bool_feature(feat_name, plain_name, define_name, res, + define_prefix); +} + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; - res = bpf_probe_large_insn_limit(ifindex); - print_bool_feature("have_large_insn_limit", + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_large_insn_limit", "Large program size limit", - "LARGE_INSN_LIMIT", - res, define_prefix); + "LARGE_INSN_LIMIT"); +} + +/* + * Probe for bounded loop support introduced in commit 2589726d12a1 + * ("bpf: introduce bounded loops"). + */ +static void +probe_bounded_loops(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_bounded_loops", + "Bounded loop support", + "BOUNDED_LOOPS"); +} + +/* + * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b + * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions"). + */ +static void +probe_v2_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v2_isa_extension", + "ISA extension v2", + "V2_ISA_EXTENSION"); +} + +/* + * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6 + * ("bpf: verifier support JMP32"). + */ +static void +probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v3_isa_extension", + "ISA extension v3", + "V3_ISA_EXTENSION"); } static void @@ -688,30 +931,47 @@ static void section_program_types(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("program_types", "Scanning eBPF program types...", "/*** eBPF program types ***/", define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) - probe_prog_type(i, supported_types, define_prefix, ifindex); + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_prog_type(prog_type, prog_type_str, supported_types, define_prefix, + ifindex); + } print_end_section(); } static void section_map_types(const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int map_type = BPF_MAP_TYPE_UNSPEC; + const char *map_type_str; print_start_section("map_types", "Scanning eBPF map types...", "/*** eBPF map types ***/", define_prefix); - for (i = BPF_MAP_TYPE_UNSPEC + 1; i < map_type_name_size; i++) - probe_map_type(i, define_prefix, ifindex); + while (true) { + map_type++; + map_type_str = libbpf_bpf_map_type_str(map_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!map_type_str) + break; + + probe_map_type(map_type, map_type_str, define_prefix, ifindex); + } print_end_section(); } @@ -719,7 +979,8 @@ static void section_map_types(const char *define_prefix, __u32 ifindex) static void section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("helpers", "Scanning eBPF helper functions...", @@ -741,9 +1002,18 @@ section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", define_prefix, define_prefix, define_prefix, define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) - probe_helpers_for_progtype(i, supported_types[i], define_prefix, + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_helpers_for_progtype(prog_type, prog_type_str, + supported_types[prog_type], + define_prefix, ifindex); + } print_end_section(); } @@ -755,6 +1025,9 @@ static void section_misc(const char *define_prefix, __u32 ifindex) "/*** eBPF misc features ***/", define_prefix); probe_large_insn_limit(define_prefix, ifindex); + probe_bounded_loops(define_prefix, ifindex); + probe_v2_isa_extension(define_prefix, ifindex); + probe_v3_isa_extension(define_prefix, ifindex); print_end_section(); } @@ -835,9 +1108,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } @@ -865,7 +1143,7 @@ exit_free: return res; #else /* Detection assumes user has specific privileges. - * We do not use libpcap so let's approximate, and restrict usage to + * We do not use libcap so let's approximate, and restrict usage to * root user only. */ if (geteuid()) { @@ -976,6 +1254,58 @@ exit_close_json: return 0; } +static const char *get_helper_name(unsigned int id) +{ + if (id >= ARRAY_SIZE(helper_name)) + return NULL; + + return helper_name[id]; +} + +static int do_list_builtins(int argc, char **argv) +{ + const char *(*get_name)(unsigned int id); + unsigned int id = 0; + + if (argc < 1) + usage(); + + if (is_prefix(*argv, "prog_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_prog_type_str; + } else if (is_prefix(*argv, "map_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_map_type_str; + } else if (is_prefix(*argv, "attach_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_attach_type_str; + } else if (is_prefix(*argv, "link_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_link_type_str; + } else if (is_prefix(*argv, "helpers")) { + get_name = get_helper_name; + } else { + p_err("expected 'prog_types', 'map_types', 'attach_types', 'link_types' or 'helpers', got: %s", *argv); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + const char *name; + + name = get_name(id++); + if (!name) + break; + if (json_output) + jsonw_string(json_wtr, name); + else + printf("%s\n", name); + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -985,9 +1315,12 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s list_builtins GROUP\n" " %1$s %2$s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" + " GROUP := { prog_types | map_types | attach_types | link_types | helpers }\n" + " " HELP_SPEC_OPTIONS " }\n" "", bin_name, argv[-2]); @@ -995,8 +1328,9 @@ static int do_help(int argc, char **argv) } static const struct cmd cmds[] = { - { "probe", do_probe }, - { "help", do_help }, + { "probe", do_probe }, + { "list_builtins", do_list_builtins }, + { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 10de76b296ba..4fa4ade1ce74 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -7,6 +7,7 @@ #include <ctype.h> #include <errno.h> #include <fcntl.h> +#include <libgen.h> #include <linux/err.h> #include <stdbool.h> #include <stdio.h> @@ -14,16 +15,15 @@ #include <unistd.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> #include <bpf/btf.h> -#include "bpf/libbpf_internal.h" #include "json_writer.h" #include "main.h" - #define MAX_OBJ_NAME_LEN 64 static void sanitize_identifier(char *name) @@ -35,6 +35,11 @@ static void sanitize_identifier(char *name) name[i] = '_'; } +static bool str_has_prefix(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} + static bool str_has_suffix(const char *str, const char *suffix) { size_t i, n1 = strlen(str), n2 = strlen(suffix); @@ -50,45 +55,91 @@ static bool str_has_suffix(const char *str, const char *suffix) return true; } +static const struct btf_type * +resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t; + + t = skip_mods_and_typedefs(btf, id, NULL); + if (!btf_is_ptr(t)) + return NULL; + + t = skip_mods_and_typedefs(btf, t->type, res_id); + + return btf_is_func_proto(t) ? t : NULL; +} + 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'; + char file_copy[PATH_MAX]; + + /* Using basename() POSIX version to be more portable. */ + strncpy(file_copy, file, PATH_MAX - 1)[PATH_MAX - 1] = '\0'; + strncpy(name, basename(file_copy), MAX_OBJ_NAME_LEN - 1)[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) +static void get_header_guard(char *guard, const char *obj_name, const char *suffix) { int i; - sprintf(guard, "__%s_SKEL_H__", obj_name); + sprintf(guard, "__%s_%s__", obj_name, suffix); for (i = 0; guard[i]; i++) guard[i] = toupper(guard[i]); } -static const char *get_map_ident(const struct bpf_map *map) +static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz) { + static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; const char *name = bpf_map__name(map); + int i, n; - if (!bpf_map__is_internal(map)) - 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; + if (!bpf_map__is_internal(map)) { + snprintf(buf, buf_sz, "%s", name); + return true; + } + + for (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) { + const char *sfx = sfxs[i], *p; + + p = strstr(name, sfx); + if (p) { + snprintf(buf, buf_sz, "%s", p + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; +} + +static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz) +{ + static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + int i, n; + + /* recognize hard coded LLVM section name */ + if (strcmp(sec_name, ".arena.1") == 0) { + /* this is the name to use in skeleton */ + snprintf(buf, buf_sz, "arena"); + return true; + } + for (i = 0, n = ARRAY_SIZE(pfxs); i < n; i++) { + const char *pfx = pfxs[i]; + + if (str_has_prefix(sec_name, pfx)) { + snprintf(buf, buf_sz, "%s", sec_name + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; } -static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args) { vprintf(fmt, args); } @@ -102,20 +153,15 @@ static int codegen_datasec_def(struct bpf_object *obj, 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 + char var_ident[256], sec_ident[256]; + bool strip_mods = false; + + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) return 0; + if (strcmp(sec_name, ".kconfig") != 0) + strip_mods = true; + printf(" struct %s__%s {\n", obj_name, sec_ident); for (i = 0; i < vlen; i++, sec_var++) { const struct btf_type *var = btf__type_by_id(btf, sec_var->type); @@ -123,16 +169,14 @@ static int codegen_datasec_def(struct bpf_object *obj, DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, .field_name = var_ident, .indent_level = 2, + .strip_mods = strip_mods, ); int need_off = sec_var->offset, align_off, align; __u32 var_type_id = var->type; - 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); - } + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; if (off > need_off) { p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", @@ -146,6 +190,20 @@ static int codegen_datasec_def(struct bpf_object *obj, var_name, align); return -EINVAL; } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; align_off = (off + align - 1) / align * align; if (align_off != need_off) { @@ -174,27 +232,174 @@ static int codegen_datasec_def(struct bpf_object *obj, return 0; } +static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident) +{ + int n = btf__type_cnt(btf), i; + char sec_ident[256]; + + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) + return t; + } + return NULL; +} + +static bool is_mmapable_map(const struct bpf_map *map, char *buf, size_t sz) +{ + size_t tmp_sz; + + if (bpf_map__type(map) == BPF_MAP_TYPE_ARENA && bpf_map__initial_value(map, &tmp_sz)) { + snprintf(buf, sz, "arena"); + return true; + } + + if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + return false; + + if (!get_map_ident(map, buf, sz)) + return false; + + return true; +} + static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) { struct btf *btf = bpf_object__btf(obj); - int n = btf__get_nr_types(btf); struct btf_dump *d; - int i, err = 0; + struct bpf_map *map; + const struct btf_type *sec; + char map_ident[256]; + int err = 0; - d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); - if (IS_ERR(d)) - return PTR_ERR(d); + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; - for (i = 1; i <= n; i++) { - const struct btf_type *t = btf__type_by_id(btf, i); + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; - if (!btf_is_datasec(t)) + sec = find_type_for_map(btf, map_ident); + + /* In some cases (e.g., sections like .rodata.cst16 containing + * compiler allocated string constants only) there will be + * special internal maps with no corresponding DATASEC BTF + * type. In such case, generate empty structs for each such + * map. It will still be memory-mapped and its contents + * accessible from user-space through BPF skeleton. + */ + if (!sec) { + printf(" struct %s__%s {\n", obj_name, map_ident); + printf(" } *%s;\n", map_ident); + } else { + err = codegen_datasec_def(obj, btf, d, sec, obj_name); + if (err) + goto out; + } + } + + +out: + btf_dump__free(d); + return err; +} + +static bool btf_is_ptr_to_func_proto(const struct btf *btf, + const struct btf_type *v) +{ + return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type)); +} + +static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec, *var; + const struct btf_var_secinfo *sec_var; + int i, err = 0, vlen; + char map_ident[256], sec_ident[256]; + bool strip_mods = false, needs_typeof = false; + const char *sec_name, *var_name; + __u32 var_type_id; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_mmapable_map(map, map_ident, sizeof(map_ident))) continue; - err = codegen_datasec_def(obj, btf, d, t, obj_name); - if (err) - goto out; + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("typeof("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); } + out: btf_dump__free(d); return err; @@ -222,8 +427,8 @@ static void codegen(const char *template, ...) } else if (c == '\n') { break; } else { - p_err("unrecognized character at pos %td in template '%s'", - src - template - 1, template); + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); free(s); exit(-1); } @@ -259,16 +464,690 @@ static void codegen(const char *template, ...) free(s); } +static void print_hex(const char *data, int data_sz) +{ + int i, len; + + for (i = 0, len = 0; i < data_sz; i++) { + int w = data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)data[i]); + } +} + +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map); + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ +static void codegen_asserts(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct bpf_map *map; + struct btf_var_secinfo *sec_var; + int i, vlen; + const struct btf_type *sec; + char map_ident[256], var_ident[256]; + + if (!btf) + return; + + codegen("\ + \n\ + __attribute__((unused)) static void \n\ + %1$s__assert(struct %1$s *s __attribute__((unused))) \n\ + { \n\ + #ifdef __cplusplus \n\ + #define _Static_assert static_assert \n\ + #endif \n\ + ", obj_name); + + bpf_object__for_each_map(map, obj) { + if (!is_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) { + /* best effort, couldn't find the type for this map */ + continue; + } + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + long var_size; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + var_size = btf__resolve_size(btf, var->type); + if (var_size < 0) + continue; + + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t_Static_assert(sizeof(s->%s->%s) == %ld, \"unexpected size of '%s'\");\n", + map_ident, var_ident, var_size, var_ident); + } + } + codegen("\ + \n\ + #ifdef __cplusplus \n\ + #undef _Static_assert \n\ + #endif \n\ + } \n\ + "); +} + +static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *tp_name; + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__%2$s__attach(struct %1$s *skel) \n\ + { \n\ + int prog_fd = skel->progs.%2$s.prog_fd; \n\ + ", obj_name, bpf_program__name(prog)); + + switch (bpf_program__type(prog)) { + case BPF_PROG_TYPE_RAW_TRACEPOINT: + tp_name = strchr(bpf_program__section_name(prog), '/') + 1; + printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER) + printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n"); + else + printf("\tint fd = skel_raw_tracepoint_open(NULL, prog_fd);\n"); + break; + default: + printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); + break; + } + codegen("\ + \n\ + \n\ + if (fd > 0) \n\ + skel->links.%1$s_fd = fd; \n\ + return fd; \n\ + } \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *skel) \n\ + { \n\ + int ret = 0; \n\ + \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + ret = ret < 0 ? ret : %1$s__%2$s__attach(skel); \n\ + ", obj_name, bpf_program__name(prog)); + } + + codegen("\ + \n\ + return ret < 0 ? ret : 0; \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *skel) \n\ + { \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->links.%1$s_fd); \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + } \n\ + "); +} + +static void codegen_destroy(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + struct bpf_map *map; + char ident[256]; + + codegen("\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + %1$s__detach(skel); \n\ + ", + obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->progs.%1$s.prog_fd); \n\ + ", bpf_program__name(prog)); + } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (bpf_map__is_internal(map) && + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n", + ident, bpf_map_mmap_sz(map)); + codegen("\ + \n\ + skel_closenz(skel->maps.%1$s.map_fd); \n\ + ", ident); + } + codegen("\ + \n\ + skel_free(skel); \n\ + } \n\ + ", + obj_name); +} + +static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) +{ + DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); + struct bpf_map *map; + char ident[256]; + int err = 0; + + err = bpf_object__gen_loader(obj, &opts); + if (err) + return err; + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto out; + } + /* If there was no error during load then gen_loader_opts + * are populated with the loader program. + */ + + /* finish generating 'struct skel' */ + codegen("\ + \n\ + }; \n\ + ", obj_name); + + + codegen_attach_detach(obj, obj_name); + + codegen_destroy(obj, obj_name); + + codegen("\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = skel_alloc(sizeof(*skel)); \n\ + if (!skel) \n\ + goto cleanup; \n\ + skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ + ", + obj_name, opts.data_sz); + bpf_object__for_each_map(map, obj) { + const void *mmap_data = NULL; + size_t mmap_size = 0; + + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + { \n\ + static const char data[] __attribute__((__aligned__(8))) = \"\\\n\ + "); + mmap_data = bpf_map__initial_value(map, &mmap_size); + print_hex(mmap_data, mmap_size); + codegen("\ + \n\ + \"; \n\ + \n\ + skel->%1$s = skel_prep_map_data((void *)data, %2$zd,\n\ + sizeof(data) - 1);\n\ + if (!skel->%1$s) \n\ + goto cleanup; \n\ + skel->maps.%1$s.initial_value = (__u64) (long) skel->%1$s;\n\ + } \n\ + ", ident, bpf_map_mmap_sz(map)); + } + codegen("\ + \n\ + return skel; \n\ + cleanup: \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *skel) \n\ + { \n\ + struct bpf_load_and_run_opts opts = {}; \n\ + int err; \n\ + static const char opts_data[] __attribute__((__aligned__(8))) = \"\\\n\ + ", + obj_name); + print_hex(opts.data, opts.data_sz); + codegen("\ + \n\ + \"; \n\ + static const char opts_insn[] __attribute__((__aligned__(8))) = \"\\\n\ + "); + print_hex(opts.insns, opts.insns_sz); + codegen("\ + \n\ + \"; \n\ + \n\ + opts.ctx = (struct bpf_loader_ctx *)skel; \n\ + opts.data_sz = sizeof(opts_data) - 1; \n\ + opts.data = (void *)opts_data; \n\ + opts.insns_sz = sizeof(opts_insn) - 1; \n\ + opts.insns = (void *)opts_insn; \n\ + \n\ + err = bpf_load_and_run(&opts); \n\ + if (err < 0) \n\ + return err; \n\ + "); + bpf_object__for_each_map(map, obj) { + const char *mmap_flags; + + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) + mmap_flags = "PROT_READ"; + else + mmap_flags = "PROT_READ | PROT_WRITE"; + + codegen("\ + \n\ + skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value, \n\ + %2$zd, %3$s, skel->maps.%1$s.map_fd);\n\ + if (!skel->%1$s) \n\ + return -ENOMEM; \n\ + ", + ident, bpf_map_mmap_sz(map), mmap_flags); + } + codegen("\ + \n\ + return 0; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = %1$s__open(); \n\ + if (!skel) \n\ + return NULL; \n\ + if (%1$s__load(skel)) { \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + return skel; \n\ + } \n\ + \n\ + ", obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + return err; +} + +static void +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +{ + struct bpf_map *map; + char ident[256]; + size_t i; + + if (!map_cnt) + return; + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } +} + +static void +codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links) +{ + struct bpf_program *prog; + int i; + + if (!prog_cnt) + return; + + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + ", + i, bpf_program__name(prog)); + + if (populate_links) { + codegen("\ + \n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + } + i++; + } +} + +static int walk_st_ops_shadow_vars(struct btf *btf, const char *ident, + const struct btf_type *map_type, __u32 map_type_id) +{ + LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, .indent_level = 3); + const struct btf_type *member_type; + __u32 offset, next_offset = 0; + const struct btf_member *m; + struct btf_dump *d = NULL; + const char *member_name; + __u32 member_type_id; + int i, err = 0, n; + int size; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + n = btf_vlen(map_type); + for (i = 0, m = btf_members(map_type); i < n; i++, m++) { + member_type = skip_mods_and_typedefs(btf, m->type, &member_type_id); + member_name = btf__name_by_offset(btf, m->name_off); + + offset = m->offset / 8; + if (next_offset < offset) + printf("\t\t\tchar __padding_%d[%d];\n", i, offset - next_offset); + + switch (btf_kind(member_type)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* scalar type */ + printf("\t\t\t"); + opts.field_name = member_name; + err = btf_dump__emit_type_decl(d, member_type_id, &opts); + if (err) { + p_err("Failed to emit type declaration for %s: %d", member_name, err); + goto out; + } + printf(";\n"); + + size = btf__resolve_size(btf, member_type_id); + if (size < 0) { + p_err("Failed to resolve size of %s: %d\n", member_name, size); + err = size; + goto out; + } + + next_offset = offset + size; + break; + + case BTF_KIND_PTR: + if (resolve_func_ptr(btf, m->type, NULL)) { + /* Function pointer */ + printf("\t\t\tstruct bpf_program *%s;\n", member_name); + + next_offset = offset + sizeof(void *); + break; + } + /* All pointer types are unsupported except for + * function pointers. + */ + fallthrough; + + default: + /* Unsupported types + * + * Types other than scalar types and function + * pointers are currently not supported in order to + * prevent conflicts in the generated code caused + * by multiple definitions. For instance, if the + * struct type FOO is used in a struct_ops map, + * bpftool has to generate definitions for FOO, + * which may result in conflicts if FOO is defined + * in different skeleton files. + */ + size = btf__resolve_size(btf, member_type_id); + if (size < 0) { + p_err("Failed to resolve size of %s: %d\n", member_name, size); + err = size; + goto out; + } + printf("\t\t\tchar __unsupported_%d[%d];\n", i, size); + + next_offset = offset + size; + break; + } + } + + /* Cannot fail since it must be a struct type */ + size = btf__resolve_size(btf, map_type_id); + if (next_offset < (__u32)size) + printf("\t\t\tchar __padding_end[%d];\n", size - next_offset); + +out: + btf_dump__free(d); + + return err; +} + +/* Generate the pointer of the shadow type for a struct_ops map. + * + * This function adds a pointer of the shadow type for a struct_ops map. + * The members of a struct_ops map can be exported through a pointer to a + * shadow type. The user can access these members through the pointer. + * + * A shadow type includes not all members, only members of some types. + * They are scalar types and function pointers. The function pointers are + * translated to the pointer of the struct bpf_program. The scalar types + * are translated to the original type without any modifiers. + * + * Unsupported types will be translated to a char array to occupy the same + * space as the original field, being renamed as __unsupported_*. The user + * should treat these fields as opaque data. + */ +static int gen_st_ops_shadow_type(const char *obj_name, struct btf *btf, const char *ident, + const struct bpf_map *map) +{ + const struct btf_type *map_type; + const char *type_name; + __u32 map_type_id; + int err; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id == 0) + return -EINVAL; + map_type = btf__type_by_id(btf, map_type_id); + if (!map_type) + return -EINVAL; + + type_name = btf__name_by_offset(btf, map_type->name_off); + + printf("\t\tstruct %s__%s__%s {\n", obj_name, ident, type_name); + + err = walk_st_ops_shadow_vars(btf, ident, map_type, map_type_id); + if (err) + return err; + + printf("\t\t} *%s;\n", ident); + + return 0; +} + +static int gen_st_ops_shadow(const char *obj_name, struct btf *btf, struct bpf_object *obj) +{ + int err, st_ops_cnt = 0; + struct bpf_map *map; + char ident[256]; + + if (!btf) + return 0; + + /* Generate the pointers to shadow types of + * struct_ops maps. + */ + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + if (st_ops_cnt == 0) /* first struct_ops map */ + printf("\tstruct {\n"); + st_ops_cnt++; + + err = gen_st_ops_shadow_type(obj_name, btf, ident, map); + if (err) + return err; + } + + if (st_ops_cnt) + printf("\t} struct_ops;\n"); + + return 0; +} + +/* Generate the code to initialize the pointers of shadow types. */ +static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj) +{ + struct bpf_map *map; + char ident[256]; + + if (!btf) + return; + + /* Initialize the pointers to_ops shadow types of + * struct_ops maps. + */ + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + codegen("\ + \n\ + obj->struct_ops.%1$s = bpf_map__initial_value(obj->maps.%1$s, NULL);\n\ + \n\ + ", ident); + } +} + 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; + size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); - char obj_name[MAX_OBJ_NAME_LEN], *obj_data; + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; - const char *file, *ident; + const char *file; + char ident[256]; struct bpf_program *prog; - int fd, len, err = -1; + int fd, err = -1; struct bpf_map *map; struct btf *btf; struct stat st; @@ -279,6 +1158,28 @@ static int do_skeleton(int argc, char **argv) } file = GET_ARG(); + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + if (argc) { p_err("extra unknown arguments"); return -1; @@ -301,18 +1202,24 @@ static int do_skeleton(int argc, char **argv) p_err("failed to mmap() %s: %s", file, strerror(errno)); goto out; } - get_obj_name(obj_name, file); + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); opts.object_name = obj_name; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_mem(obj_data, file_sz, &opts); - if (IS_ERR(obj)) { - obj = NULL; - p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); + if (!obj) { + char err_buf[256]; + + err = -errno; + libbpf_strerror(err, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); goto out; } bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); - if (!ident) { + if (!get_map_ident(map, ident, sizeof(ident))) { p_err("ignoring unrecognized internal map '%s'...", bpf_map__name(map)); continue; @@ -323,15 +1230,32 @@ static int do_skeleton(int argc, char **argv) prog_cnt++; } - get_header_guard(header_guard, obj_name); - codegen("\ + get_header_guard(header_guard, obj_name, "SKEL_H"); + if (use_loader) { + codegen("\ \n\ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <bpf/skel_internal.h> \n\ \n\ - /* THIS FILE IS AUTOGENERATED! */ \n\ + struct %1$s { \n\ + struct bpf_loader_ctx ctx; \n\ + ", + obj_name, header_guard + ); + } else { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ #ifndef %2$s \n\ #define %2$s \n\ \n\ + #include <errno.h> \n\ #include <stdlib.h> \n\ #include <bpf/libbpf.h> \n\ \n\ @@ -340,43 +1264,72 @@ static int do_skeleton(int argc, char **argv) struct bpf_object *obj; \n\ ", obj_name, header_guard - ); + ); + } if (map_cnt) { printf("\tstruct {\n"); bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); - if (!ident) + if (!get_map_ident(map, ident, sizeof(ident))) continue; - printf("\t\tstruct bpf_map *%s;\n", ident); + if (use_loader) + printf("\t\tstruct bpf_map_desc %s;\n", ident); + else + printf("\t\tstruct bpf_map *%s;\n", ident); } printf("\t} maps;\n"); } + btf = bpf_object__btf(obj); + err = gen_st_ops_shadow(obj_name, btf, obj); + if (err) + goto out; + if (prog_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_program *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tstruct bpf_prog_desc %s;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); } printf("\t} progs;\n"); printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_link *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tint %s_fd;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); } printf("\t} links;\n"); } - btf = bpf_object__btf(obj); if (btf) { err = codegen_datasecs(obj, obj_name); if (err) goto out; } + if (use_loader) { + err = gen_trace(obj, obj_name, header_guard); + goto out; + } codegen("\ \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\ + static inline struct %1$s *open_and_load(); \n\ + static inline int load(struct %1$s *skel); \n\ + static inline int attach(struct %1$s *skel); \n\ + static inline void detach(struct %1$s *skel); \n\ + static inline void destroy(struct %1$s *skel); \n\ + static inline const void *elf_bytes(size_t *sz); \n\ + #endif /* __cplusplus */ \n\ }; \n\ \n\ static void \n\ @@ -396,18 +1349,32 @@ static int do_skeleton(int argc, char **argv) %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ { \n\ struct %1$s *obj; \n\ + int err; \n\ \n\ - obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ - if (!obj) \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ return NULL; \n\ - if (%1$s__create_skeleton(obj)) \n\ - goto err; \n\ - if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ - goto err; \n\ + } \n\ \n\ + err = %1$s__create_skeleton(obj); \n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + ", obj_name); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ return obj; \n\ - err: \n\ + err_out: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ @@ -427,12 +1394,15 @@ static int do_skeleton(int argc, char **argv) %1$s__open_and_load(void) \n\ { \n\ struct %1$s *obj; \n\ + int err; \n\ \n\ obj = %1$s__open(); \n\ if (!obj) \n\ return NULL; \n\ - if (%1$s__load(obj)) { \n\ + err = %1$s__load(obj); \n\ + if (err) { \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ return obj; \n\ @@ -447,7 +1417,7 @@ static int do_skeleton(int argc, char **argv) static inline void \n\ %1$s__detach(struct %1$s *obj) \n\ { \n\ - return bpf_object__detach_skeleton(obj->skeleton); \n\ + bpf_object__detach_skeleton(obj->skeleton); \n\ } \n\ ", obj_name @@ -456,15 +1426,19 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ static inline int \n\ %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ - s = (typeof(s))calloc(1, sizeof(*s)); \n\ - if (!s) \n\ - return -1; \n\ - obj->skeleton = s; \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -472,104 +1446,376 @@ static int do_skeleton(int argc, char **argv) ", obj_name ); - if (map_cnt) { - codegen("\ - \n\ + + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + + codegen("\ + \n\ \n\ - /* maps */ \n\ - s->map_cnt = %zu; \n\ - s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ - goto err; \n\ - ", - map_cnt - ); - i = 0; - bpf_object__for_each_map(map, obj) { - ident = get_map_ident(map); + s->data = %1$s__elf_bytes(&s->data_sz); \n\ + \n\ + obj->skeleton = s; \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return err; \n\ + } \n\ + \n\ + static inline const void *%1$s__elf_bytes(size_t *sz) \n\ + { \n\ + static const char data[] __attribute__((__aligned__(8))) = \"\\\n\ + ", + obj_name + ); - if (!ident) - continue; + /* embed contents of BPF object file */ + print_hex(obj_data, file_sz); - codegen("\ - \n\ + codegen("\ + \n\ + \"; \n\ \n\ - s->maps[%zu].name = \"%s\"; \n\ - s->maps[%zu].map = &obj->maps.%s; \n\ - ", - i, bpf_map__name(map), i, ident); - /* memory-mapped internal maps */ - if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { - printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", - i, ident); + *sz = sizeof(data) - 1; \n\ + return (const void *)data; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object_open_opts *opts) { return %1$s__open_opts(opts); }\n\ + struct %1$s *%1$s::open_and_load() { return %1$s__open_and_load(); } \n\ + int %1$s::load(struct %1$s *skel) { return %1$s__load(skel); } \n\ + int %1$s::attach(struct %1$s *skel) { return %1$s__attach(skel); } \n\ + void %1$s::detach(struct %1$s *skel) { %1$s__detach(skel); } \n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); } \n\ + const void *%1$s::elf_bytes(size_t *sz) { return %1$s__elf_bytes(sz); } \n\ + #endif /* __cplusplus */ \n\ + \n\ + ", + obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %1$s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; } - i++; + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; } + + NEXT_ARG(); } - if (prog_cnt) { - codegen("\ - \n\ + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ \n\ - /* 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\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \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++; + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); } + printf("\t} maps;\n"); } + + err = gen_st_ops_shadow(obj_name, btf, obj); + if (err) + goto out; + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + err = codegen_subskel_datasecs(obj, obj_name); + if (err) + goto out; + + /* emit code that will allocate enough storage for all symbols */ codegen("\ \n\ \n\ - s->data_sz = %d; \n\ - s->data = (void *)\"\\ \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object *src);\n\ + static inline void destroy(struct %1$s *skel); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static inline void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + if (skel->subskel) \n\ + bpf_object__destroy_subskeleton(skel->subskel);\n\ + free(skel); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(const struct bpf_object *src) \n\ + { \n\ + struct %1$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ ", - file_sz); + obj_name, var_cnt + ); - /* embed contents of BPF object file */ - for (i = 0, len = 0; i < file_sz; i++) { - int w = obj_data[i] ? 4 : 2; + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; - len += w; - if (len > 78) { - printf("\\\n"); - len = w; + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; } - if (!obj_data[i]) - printf("\\0"); - else - printf("\\x%02x", (unsigned char)obj_data[i]); } + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + codegen("\ \n\ - \"; \n\ \n\ - return 0; \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + "); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ + return obj; \n\ err: \n\ - bpf_object__destroy_skeleton(s); \n\ - return -1; \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ } \n\ \n\ - #endif /* %s */ \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ ", - header_guard); + obj_name, header_guard); err = 0; out: bpf_object__close(obj); @@ -579,6 +1825,47 @@ out: return err; } +static int do_object(int argc, char **argv) +{ + struct bpf_linker *linker; + const char *output_file, *file; + int err = 0; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + output_file = GET_ARG(); + + linker = bpf_linker__new(output_file, NULL); + if (!linker) { + p_err("failed to create BPF linker instance"); + return -1; + } + + while (argc) { + file = GET_ARG(); + + err = bpf_linker__add_file(linker, file, NULL); + if (err) { + p_err("failed to link '%s': %s (%d)", file, strerror(errno), errno); + goto out; + } + } + + err = bpf_linker__finalize(linker); + if (err) { + p_err("failed to finalize ELF file: %s (%d)", strerror(errno), errno); + goto out; + } + + err = 0; +out: + bpf_linker__free(linker); + return err; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -587,19 +1874,713 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %1$s %2$s skeleton FILE\n" + "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" + " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" " %1$s %2$s help\n" "\n" - " " HELP_SPEC_OPTIONS "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-L|--use-loader} }\n" "", bin_name, "gen"); return 0; } +static int btf_save_raw(const struct btf *btf, const char *path) +{ + const void *data; + FILE *f = NULL; + __u32 data_sz; + int err = 0; + + data = btf__raw_data(btf, &data_sz); + if (!data) + return -ENOMEM; + + f = fopen(path, "wb"); + if (!f) + return -errno; + + if (fwrite(data, 1, data_sz, f) != data_sz) + err = -errno; + + fclose(f); + return err; +} + +struct btfgen_info { + struct btf *src_btf; + struct btf *marked_btf; /* btf structure used to mark used types */ +}; + +static size_t btfgen_hash_fn(long key, void *ctx) +{ + return key; +} + +static bool btfgen_equal_fn(long k1, long k2, void *ctx) +{ + return k1 == k2; +} + +static void btfgen_free_info(struct btfgen_info *info) +{ + if (!info) + return; + + btf__free(info->src_btf); + btf__free(info->marked_btf); + + free(info); +} + +static struct btfgen_info * +btfgen_new_info(const char *targ_btf_path) +{ + struct btfgen_info *info; + int err; + + info = calloc(1, sizeof(*info)); + if (!info) + return NULL; + + info->src_btf = btf__parse(targ_btf_path, NULL); + if (!info->src_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + info->marked_btf = btf__parse(targ_btf_path, NULL); + if (!info->marked_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + return info; + +err_out: + btfgen_free_info(info); + errno = -err; + return NULL; +} + +#define MARKED UINT32_MAX + +static void btfgen_mark_member(struct btfgen_info *info, int type_id, int idx) +{ + const struct btf_type *t = btf__type_by_id(info->marked_btf, type_id); + struct btf_member *m = btf_members(t) + idx; + + m->name_off = MARKED; +} + +static int +btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_pointers) +{ + const struct btf_type *btf_type = btf__type_by_id(info->src_btf, type_id); + struct btf_type *cloned_type; + struct btf_param *param; + struct btf_array *array; + int err, i; + + if (type_id == 0) + return 0; + + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *) btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + /* recursively mark other types needed by it */ + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + break; + case BTF_KIND_PTR: + if (follow_pointers) { + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + } + break; + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + + /* mark array type */ + err = btfgen_mark_type(info, array->type, follow_pointers); + /* mark array's index type */ + err = err ? : btfgen_mark_type(info, array->index_type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_FUNC_PROTO: + /* mark ret type */ + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < btf_vlen(btf_type); i++) { + err = btfgen_mark_type(info, param->type, follow_pointers); + if (err) + return err; + param++; + } + break; + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + struct btf *btf = info->src_btf; + const struct btf_type *btf_type; + struct btf_member *btf_member; + struct btf_array *array; + unsigned int type_id = targ_spec->root_type_id; + int idx, err; + + /* mark root type */ + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + + /* mark types for complex types (arrays, unions, structures) */ + for (int i = 1; i < targ_spec->raw_len; i++) { + /* skip typedefs and mods */ + while (btf_is_mod(btf_type) || btf_is_typedef(btf_type)) { + type_id = btf_type->type; + btf_type = btf__type_by_id(btf, type_id); + } + + switch (btf_kind(btf_type)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + idx = targ_spec->raw_spec[i]; + btf_member = btf_members(btf_type) + idx; + + /* mark member */ + btfgen_mark_member(info, type_id, idx); + + /* mark member's type */ + type_id = btf_member->type; + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + type_id = array->type; + btf_type = btf__type_by_id(btf, type_id); + break; + default: + p_err("unsupported kind: %s (%d)", + btf_kind_str(btf_type), btf_type->type); + return -EINVAL; + } + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + * + * The `behind_ptr` argument is used to stop marking of composite types reached + * through a pointer. This way, we can keep BTF size in check while providing + * reasonable match semantics. + */ +static int btfgen_mark_type_match(struct btfgen_info *info, __u32 type_id, bool behind_ptr) +{ + const struct btf_type *btf_type; + struct btf *btf = info->src_btf; + struct btf_type *cloned_type; + int i, err; + + if (type_id == 0) + return 0; + + btf_type = btf__type_by_id(btf, type_id); + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *)btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(btf_type); + __u16 vlen = btf_vlen(btf_type); + + if (behind_ptr) + break; + + for (i = 0; i < vlen; i++, m++) { + /* mark member */ + btfgen_mark_member(info, type_id, i); + + /* mark member's type */ + err = btfgen_mark_type_match(info, m->type, false); + if (err) + return err; + } + break; + } + case BTF_KIND_CONST: + case BTF_KIND_FWD: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + return btfgen_mark_type_match(info, btf_type->type, behind_ptr); + case BTF_KIND_PTR: + return btfgen_mark_type_match(info, btf_type->type, true); + case BTF_KIND_ARRAY: { + struct btf_array *array; + + array = btf_array(btf_type); + /* mark array type */ + err = btfgen_mark_type_match(info, array->type, false); + /* mark array's index type */ + err = err ? : btfgen_mark_type_match(info, array->index_type, false); + if (err) + return err; + break; + } + case BTF_KIND_FUNC_PROTO: { + __u16 vlen = btf_vlen(btf_type); + struct btf_param *param; + + /* mark ret type */ + err = btfgen_mark_type_match(info, btf_type->type, false); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < vlen; i++) { + err = btfgen_mark_type_match(info, param->type, false); + if (err) + return err; + param++; + } + break; + } + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + */ +static int btfgen_record_type_match_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type_match(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, true); +} + +static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res) +{ + switch (res->relo_kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: + return btfgen_record_field_relo(info, res); + case BPF_CORE_TYPE_ID_LOCAL: /* BPF_CORE_TYPE_ID_LOCAL doesn't require kernel BTF */ + return 0; + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: + return btfgen_record_type_relo(info, res); + case BPF_CORE_TYPE_MATCHES: + return btfgen_record_type_match_relo(info, res); + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: + return btfgen_record_enumval_relo(info, res); + default: + return -EINVAL; + } +} + +static struct bpf_core_cand_list * +btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id) +{ + const struct btf_type *local_type; + struct bpf_core_cand_list *cands = NULL; + struct bpf_core_cand local_cand = {}; + size_t local_essent_len; + const char *local_name; + int err; + + local_cand.btf = local_btf; + local_cand.id = local_id; + + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) { + err = -EINVAL; + goto err_out; + } + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (!local_name) { + err = -EINVAL; + goto err_out; + } + local_essent_len = bpf_core_essential_name_len(local_name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return NULL; + + err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + return cands; + +err_out: + bpf_core_free_cands(cands); + errno = -err; + return NULL; +} + +/* Record relocation information for a single BPF object */ +static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_core_relo *relo; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct btf_ext *btf_ext = NULL; + unsigned int relo_idx; + struct btf *btf = NULL; + size_t i; + int err; + + btf = btf__parse(obj_path, &btf_ext); + if (!btf) { + err = -errno; + p_err("failed to parse BPF object '%s': %s", obj_path, strerror(errno)); + return err; + } + + if (!btf_ext) { + p_err("failed to parse BPF object '%s': section %s not found", + obj_path, BTF_EXT_ELF_SEC); + err = -EINVAL; + goto out; + } + + if (btf_ext->core_relo_info.len == 0) { + err = 0; + goto out; + } + + cand_cache = hashmap__new(btfgen_hash_fn, btfgen_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + for_each_btf_ext_rec(seg, sec, relo_idx, relo) { + struct bpf_core_spec specs_scratch[3] = {}; + struct bpf_core_relo_res targ_res = {}; + struct bpf_core_cand_list *cands = NULL; + const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off); + + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && + !hashmap__find(cand_cache, relo->type_id, &cands)) { + cands = btfgen_find_cands(btf, info->src_btf, relo->type_id); + if (!cands) { + err = -errno; + goto out; + } + + err = hashmap__set(cand_cache, relo->type_id, cands, + NULL, NULL); + if (err) + goto out; + } + + err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands, + specs_scratch, &targ_res); + if (err) + goto out; + + /* specs_scratch[2] is the target spec */ + err = btfgen_record_reloc(info, &specs_scratch[2]); + if (err) + goto out; + } + } + +out: + btf__free(btf); + btf_ext__free(btf_ext); + + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->pvalue); + } + hashmap__free(cand_cache); + } + + return err; +} + +static int btfgen_remap_id(__u32 *type_id, void *ctx) +{ + unsigned int *ids = ctx; + + *type_id = ids[*type_id]; + + return 0; +} + +/* Generate BTF from relocation information previously recorded */ +static struct btf *btfgen_get_btf(struct btfgen_info *info) +{ + struct btf *btf_new = NULL; + unsigned int *ids = NULL; + unsigned int i, n = btf__type_cnt(info->marked_btf); + int err = 0; + + btf_new = btf__new_empty(); + if (!btf_new) { + err = -errno; + goto err_out; + } + + ids = calloc(n, sizeof(*ids)); + if (!ids) { + err = -errno; + goto err_out; + } + + /* first pass: add all marked types to btf_new and add their new ids to the ids map */ + for (i = 1; i < n; i++) { + const struct btf_type *cloned_type, *type; + const char *name; + int new_id; + + cloned_type = btf__type_by_id(info->marked_btf, i); + + if (cloned_type->name_off != MARKED) + continue; + + type = btf__type_by_id(info->src_btf, i); + + /* add members for struct and union */ + if (btf_is_composite(type)) { + struct btf_member *cloned_m, *m; + unsigned short vlen; + int idx_src; + + name = btf__str_by_offset(info->src_btf, type->name_off); + + if (btf_is_struct(type)) + err = btf__add_struct(btf_new, name, type->size); + else + err = btf__add_union(btf_new, name, type->size); + + if (err < 0) + goto err_out; + new_id = err; + + cloned_m = btf_members(cloned_type); + m = btf_members(type); + vlen = btf_vlen(cloned_type); + for (idx_src = 0; idx_src < vlen; idx_src++, cloned_m++, m++) { + /* add only members that are marked as used */ + if (cloned_m->name_off != MARKED) + continue; + + name = btf__str_by_offset(info->src_btf, m->name_off); + err = btf__add_field(btf_new, name, m->type, + btf_member_bit_offset(cloned_type, idx_src), + btf_member_bitfield_size(cloned_type, idx_src)); + if (err < 0) + goto err_out; + } + } else { + err = btf__add_type(btf_new, info->src_btf, type); + if (err < 0) + goto err_out; + new_id = err; + } + + /* add ID mapping */ + ids[i] = new_id; + } + + /* second pass: fix up type ids */ + for (i = 1; i < btf__type_cnt(btf_new); i++) { + struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i); + + err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids); + if (err) + goto err_out; + } + + free(ids); + return btf_new; + +err_out: + btf__free(btf_new); + free(ids); + errno = -err; + return NULL; +} + +/* Create minimized BTF file for a set of BPF objects. + * + * The BTFGen algorithm is divided in two main parts: (1) collect the + * BTF types that are involved in relocations and (2) generate the BTF + * object using the collected types. + * + * In order to collect the types involved in the relocations, we parse + * the BTF and BTF.ext sections of the BPF objects and use + * bpf_core_calc_relo_insn() to get the target specification, this + * indicates how the types and fields are used in a relocation. + * + * Types are recorded in different ways according to the kind of the + * relocation. For field-based relocations only the members that are + * actually used are saved in order to reduce the size of the generated + * BTF file. For type-based relocations empty struct / unions are + * generated and for enum-based relocations the whole type is saved. + * + * The second part of the algorithm generates the BTF object. It creates + * an empty BTF object and fills it with the types recorded in the + * previous step. This function takes care of only adding the structure + * and union members that were marked as used and it also fixes up the + * type IDs on the generated BTF object. + */ +static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[]) +{ + struct btfgen_info *info; + struct btf *btf_new = NULL; + int err, i; + + info = btfgen_new_info(src_btf); + if (!info) { + err = -errno; + p_err("failed to allocate info structure: %s", strerror(errno)); + goto out; + } + + for (i = 0; objspaths[i] != NULL; i++) { + err = btfgen_record_obj(info, objspaths[i]); + if (err) { + p_err("error recording relocations for %s: %s", objspaths[i], + strerror(errno)); + goto out; + } + } + + btf_new = btfgen_get_btf(info); + if (!btf_new) { + err = -errno; + p_err("error generating BTF: %s", strerror(errno)); + goto out; + } + + err = btf_save_raw(btf_new, dst_btf); + if (err) { + p_err("error saving btf file: %s", strerror(errno)); + goto out; + } + +out: + btf__free(btf_new); + btfgen_free_info(info); + + return err; +} + +static int do_min_core_btf(int argc, char **argv) +{ + const char *input, *output, **objs; + int i, err; + + if (!REQ_ARGS(3)) { + usage(); + return -1; + } + + input = GET_ARG(); + output = GET_ARG(); + + objs = (const char **) calloc(argc + 1, sizeof(*objs)); + if (!objs) { + p_err("failed to allocate array for object names"); + return -ENOMEM; + } + + i = 0; + while (argc) + objs[i++] = GET_ARG(); + + err = minimize_btf(input, output, objs); + free(objs); + return err; +} + static const struct cmd cmds[] = { - { "skeleton", do_skeleton }, - { "help", do_help }, + { "object", do_object }, + { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, + { "min_core_btf", do_min_core_btf}, + { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 33240fcc6319..6b0e5202ca7a 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (C) 2020 Facebook +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif +#include <errno.h> +#include <unistd.h> #include <linux/err.h> #include <bpf/libbpf.h> @@ -9,11 +13,13 @@ static int do_pin(int argc, char **argv) { + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, iter_opts); + union bpf_iter_link_info linfo; const char *objfile, *path; struct bpf_program *prog; struct bpf_object *obj; struct bpf_link *link; - int err; + int err = -1, map_fd = -1; if (!REQ_ARGS(2)) usage(); @@ -21,10 +27,32 @@ static int do_pin(int argc, char **argv) objfile = GET_ARG(); path = GET_ARG(); + /* optional arguments */ + if (argc) { + if (is_prefix(*argv, "map")) { + NEXT_ARG(); + + if (!REQ_ARGS(2)) { + p_err("incorrect map spec"); + return -1; + } + + map_fd = map_parse_fd(&argc, &argv); + if (map_fd < 0) + return -1; + + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + iter_opts.link_info = &linfo; + iter_opts.link_info_len = sizeof(linfo); + } + } + obj = bpf_object__open(objfile); - if (IS_ERR(obj)) { + if (!obj) { + err = -errno; p_err("can't open objfile %s", objfile); - return -1; + goto close_map_fd; } err = bpf_object__load(obj); @@ -33,21 +61,22 @@ static int do_pin(int argc, char **argv) goto close_obj; } - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); if (!prog) { + err = -errno; p_err("can't find bpf program in objfile %s", objfile); goto close_obj; } - link = bpf_program__attach_iter(prog, NULL); - if (IS_ERR(link)) { - err = PTR_ERR(link); + link = bpf_program__attach_iter(prog, &iter_opts); + if (!link) { + err = -errno; p_err("attach_iter failed for program %s", bpf_program__name(prog)); goto close_obj; } - err = mount_bpffs_for_pin(path); + err = mount_bpffs_for_pin(path, false); if (err) goto close_link; @@ -62,14 +91,20 @@ close_link: bpf_link__destroy(link); close_obj: bpf_object__close(obj); +close_map_fd: + if (map_fd >= 0) + close(map_fd); return err; } static int do_help(int argc, char **argv) { fprintf(stderr, - "Usage: %1$s %2$s pin OBJ PATH\n" + "Usage: %1$s %2$s pin OBJ PATH [map MAP]\n" " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_OPTIONS " }\n" "", bin_name, "iter"); diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index e7e7eee9f172..7b8d9ec89ebd 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -11,43 +11,159 @@ * Licensed under the GNU General Public License, version 2.0 (GPLv2) */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <stdio.h> #include <stdarg.h> #include <stdint.h> #include <stdlib.h> -#include <assert.h> #include <unistd.h> #include <string.h> -#include <bfd.h> -#include <dis-asm.h> #include <sys/stat.h> #include <limits.h> #include <bpf/libbpf.h> +#ifdef HAVE_LLVM_SUPPORT +#include <llvm-c/Core.h> +#include <llvm-c/Disassembler.h> +#include <llvm-c/Target.h> +#include <llvm-c/TargetMachine.h> +#endif + +#ifdef HAVE_LIBBFD_SUPPORT +#include <bfd.h> +#include <dis-asm.h> +#include <tools/dis-asm-compat.h> +#endif + #include "json_writer.h" #include "main.h" -static void get_exec_path(char *tpath, size_t size) +static int oper_count; + +#ifdef HAVE_LLVM_SUPPORT +#define DISASM_SPACER + +typedef LLVMDisasmContextRef disasm_ctx_t; + +static int printf_json(char *s) +{ + s = strtok(s, " \t"); + jsonw_string_field(json_wtr, "operation", s); + + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count = 1; + + while ((s = strtok(NULL, " \t,()")) != 0) { + jsonw_string(json_wtr, s); + oper_count++; + } + return 0; +} + +/* This callback to set the ref_type is necessary to have the LLVM disassembler + * print PC-relative addresses instead of byte offsets for branch instruction + * targets. + */ +static const char * +symbol_lookup_callback(__maybe_unused void *disasm_info, + __maybe_unused uint64_t ref_value, + uint64_t *ref_type, __maybe_unused uint64_t ref_PC, + __maybe_unused const char **ref_name) +{ + *ref_type = LLVMDisassembler_ReferenceType_InOut_None; + return NULL; +} + +static int +init_context(disasm_ctx_t *ctx, const char *arch, + __maybe_unused const char *disassembler_options, + __maybe_unused unsigned char *image, __maybe_unused ssize_t len) +{ + char *triple; + + if (arch) + triple = LLVMNormalizeTargetTriple(arch); + else + triple = LLVMGetDefaultTargetTriple(); + if (!triple) { + p_err("Failed to retrieve triple"); + return -1; + } + *ctx = LLVMCreateDisasm(triple, NULL, 0, NULL, symbol_lookup_callback); + LLVMDisposeMessage(triple); + + if (!*ctx) { + p_err("Failed to create disassembler"); + return -1; + } + + return 0; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + LLVMDisposeMessage(*ctx); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, unsigned char *image, ssize_t len, int pc) +{ + char buf[256]; + int count; + + count = LLVMDisasmInstruction(*ctx, image + pc, len - pc, pc, + buf, sizeof(buf)); + if (json_output) + printf_json(buf); + else + printf("%s", buf); + + return count; +} + +int disasm_init(void) +{ + LLVMInitializeAllTargetInfos(); + LLVMInitializeAllTargetMCs(); + LLVMInitializeAllDisassemblers(); + return 0; +} +#endif /* HAVE_LLVM_SUPPORT */ + +#ifdef HAVE_LIBBFD_SUPPORT +#define DISASM_SPACER "\t" + +typedef struct { + struct disassemble_info *info; + disassembler_ftype disassemble; + bfd *bfdf; +} disasm_ctx_t; + +static int get_exec_path(char *tpath, size_t size) { const char *path = "/proc/self/exe"; ssize_t len; len = readlink(path, tpath, size - 1); - assert(len > 0); + if (len <= 0) + return -1; + tpath[len] = 0; + + return 0; } -static int oper_count; -static int fprintf_json(void *out, const char *fmt, ...) +static int printf_json(void *out, const char *fmt, va_list ap) { - va_list ap; char *s; + int err; - va_start(ap, fmt); - if (vasprintf(&s, fmt, ap) < 0) + err = vasprintf(&s, fmt, ap); + if (err < 0) return -1; - va_end(ap); if (!oper_count) { int i; @@ -71,37 +187,72 @@ static int fprintf_json(void *out, const char *fmt, ...) return 0; } -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum) +static int fprintf_json(void *out, const char *fmt, ...) { - const struct bpf_line_info *linfo = NULL; - disassembler_ftype disassemble; - struct disassemble_info info; - unsigned int nr_skip = 0; - int count, i, pc = 0; + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int init_context(disasm_ctx_t *ctx, const char *arch, + const char *disassembler_options, + unsigned char *image, ssize_t len) +{ + struct disassemble_info *info; char tpath[PATH_MAX]; bfd *bfdf; - if (!len) - return; - memset(tpath, 0, sizeof(tpath)); - get_exec_path(tpath, sizeof(tpath)); + if (get_exec_path(tpath, sizeof(tpath))) { + p_err("failed to create disassembler (get_exec_path)"); + return -1; + } + + ctx->bfdf = bfd_openr(tpath, NULL); + if (!ctx->bfdf) { + p_err("failed to create disassembler (bfd_openr)"); + return -1; + } + if (!bfd_check_format(ctx->bfdf, bfd_object)) { + p_err("failed to create disassembler (bfd_check_format)"); + goto err_close; + } + bfdf = ctx->bfdf; - bfdf = bfd_openr(tpath, NULL); - assert(bfdf); - assert(bfd_check_format(bfdf, bfd_object)); + ctx->info = malloc(sizeof(struct disassemble_info)); + if (!ctx->info) { + p_err("mem alloc failed"); + goto err_close; + } + info = ctx->info; if (json_output) - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf_json); + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); else - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf); + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); /* Update architecture info for offload. */ if (arch) { @@ -111,28 +262,77 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, bfdf->arch_info = inf; } else { p_err("No libbfd support for %s", arch); - return; + goto err_free; } } - info.arch = bfd_get_arch(bfdf); - info.mach = bfd_get_mach(bfdf); + info->arch = bfd_get_arch(bfdf); + info->mach = bfd_get_mach(bfdf); if (disassembler_options) - info.disassembler_options = disassembler_options; - info.buffer = image; - info.buffer_length = len; + info->disassembler_options = disassembler_options; + info->buffer = image; + info->buffer_length = len; - disassemble_init_for_target(&info); + disassemble_init_for_target(info); #ifdef DISASM_FOUR_ARGS_SIGNATURE - disassemble = disassembler(info.arch, - bfd_big_endian(bfdf), - info.mach, - bfdf); + ctx->disassemble = disassembler(info->arch, + bfd_big_endian(bfdf), + info->mach, + bfdf); #else - disassemble = disassembler(bfdf); + ctx->disassemble = disassembler(bfdf); #endif - assert(disassemble); + if (!ctx->disassemble) { + p_err("failed to create disassembler"); + goto err_free; + } + return 0; + +err_free: + free(info); +err_close: + bfd_close(ctx->bfdf); + return -1; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + free(ctx->info); + bfd_close(ctx->bfdf); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, __maybe_unused unsigned char *image, + __maybe_unused ssize_t len, int pc) +{ + return ctx->disassemble(pc, ctx->info); +} + +int disasm_init(void) +{ + bfd_init(); + return 0; +} +#endif /* HAVE_LIBBPFD_SUPPORT */ + +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) +{ + const struct bpf_line_info *linfo = NULL; + unsigned int nr_skip = 0; + int count, i, pc = 0; + disasm_ctx_t ctx; + + if (!len) + return -1; + + if (init_context(&ctx, arch, disassembler_options, image, len)) + return -1; if (json_output) jsonw_start_array(json_wtr); @@ -157,10 +357,11 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, if (linfo) btf_dump_linfo_plain(btf, linfo, "; ", linum); - printf("%4x:\t", pc); + printf("%4x:" DISASM_SPACER, pc); } - count = disassemble(pc, &info); + count = disassemble_insn(&ctx, image, len, pc); + if (json_output) { /* Operand array, was started in fprintf_json. Before * that, make sure we have a _null_ value if no operand @@ -196,11 +397,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, if (json_output) jsonw_end_array(json_wtr); - bfd_close(bfdf); -} + destroy_context(&ctx); -int disasm_init(void) -{ - bfd_init(); return 0; } diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c index 86501cd3c763..be379613d118 100644 --- a/tools/bpf/bpftool/json_writer.c +++ b/tools/bpf/bpftool/json_writer.c @@ -75,14 +75,11 @@ static void jsonw_puts(json_writer_t *self, const char *str) fputs("\\b", self->out); break; case '\\': - fputs("\\n", self->out); + fputs("\\\\", self->out); break; case '"': fputs("\\\"", self->out); break; - case '\'': - fputs("\\\'", self->out); - break; default: putc(*str, self->out); } @@ -119,6 +116,12 @@ void jsonw_pretty(json_writer_t *self, bool on) self->pretty = on; } +void jsonw_reset(json_writer_t *self) +{ + assert(self->depth == 0); + self->sep = '\0'; +} + /* Basic blocks */ static void jsonw_begin(json_writer_t *self, int c) { diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h index 35cf1f00f96c..5aaffd3b837b 100644 --- a/tools/bpf/bpftool/json_writer.h +++ b/tools/bpf/bpftool/json_writer.h @@ -14,6 +14,7 @@ #include <stdbool.h> #include <stdint.h> #include <stdarg.h> +#include <stdio.h> #include <linux/compiler.h> /* Opaque class structure */ @@ -27,6 +28,9 @@ void jsonw_destroy(json_writer_t **self_p); /* Cause output to have pretty whitespace */ void jsonw_pretty(json_writer_t *self, bool on); +/* Reset separator to create new JSON */ +void jsonw_reset(json_writer_t *self); + /* Add property name */ void jsonw_name(json_writer_t *self, const char *name); diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index fca57ee8fafe..afde9d0c2ea1 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -2,26 +2,96 @@ /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> +#include <linux/netfilter.h> +#include <linux/netfilter_arp.h> +#include <linux/perf_event.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> #include <bpf/bpf.h> +#include <bpf/hashmap.h> #include "json_writer.h" #include "main.h" +#include "xlated_dumper.h" -static const char * const link_type_name[] = { - [BPF_LINK_TYPE_UNSPEC] = "unspec", - [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_LINK_TYPE_TRACING] = "tracing", - [BPF_LINK_TYPE_CGROUP] = "cgroup", - [BPF_LINK_TYPE_ITER] = "iter", - [BPF_LINK_TYPE_NETNS] = "netns", +#define PERF_HW_CACHE_LEN 128 + +static struct hashmap *link_table; +static struct dump_data dd; + +static const char *perf_type_name[PERF_TYPE_MAX] = { + [PERF_TYPE_HARDWARE] = "hardware", + [PERF_TYPE_SOFTWARE] = "software", + [PERF_TYPE_TRACEPOINT] = "tracepoint", + [PERF_TYPE_HW_CACHE] = "hw-cache", + [PERF_TYPE_RAW] = "raw", + [PERF_TYPE_BREAKPOINT] = "breakpoint", +}; + +const char *event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = "cpu-cycles", + [PERF_COUNT_HW_INSTRUCTIONS] = "instructions", + [PERF_COUNT_HW_CACHE_REFERENCES] = "cache-references", + [PERF_COUNT_HW_CACHE_MISSES] = "cache-misses", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "branch-instructions", + [PERF_COUNT_HW_BRANCH_MISSES] = "branch-misses", + [PERF_COUNT_HW_BUS_CYCLES] = "bus-cycles", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "stalled-cycles-frontend", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "stalled-cycles-backend", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "ref-cycles", +}; + +const char *event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = "cpu-clock", + [PERF_COUNT_SW_TASK_CLOCK] = "task-clock", + [PERF_COUNT_SW_PAGE_FAULTS] = "page-faults", + [PERF_COUNT_SW_CONTEXT_SWITCHES] = "context-switches", + [PERF_COUNT_SW_CPU_MIGRATIONS] = "cpu-migrations", + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = "minor-faults", + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = "major-faults", + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = "alignment-faults", + [PERF_COUNT_SW_EMULATION_FAULTS] = "emulation-faults", + [PERF_COUNT_SW_DUMMY] = "dummy", + [PERF_COUNT_SW_BPF_OUTPUT] = "bpf-output", + [PERF_COUNT_SW_CGROUP_SWITCHES] = "cgroup-switches", +}; + +const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] = { + [PERF_COUNT_HW_CACHE_L1D] = "L1-dcache", + [PERF_COUNT_HW_CACHE_L1I] = "L1-icache", + [PERF_COUNT_HW_CACHE_LL] = "LLC", + [PERF_COUNT_HW_CACHE_DTLB] = "dTLB", + [PERF_COUNT_HW_CACHE_ITLB] = "iTLB", + [PERF_COUNT_HW_CACHE_BPU] = "branch", + [PERF_COUNT_HW_CACHE_NODE] = "node", +}; + +const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] = { + [PERF_COUNT_HW_CACHE_OP_READ] = "load", + [PERF_COUNT_HW_CACHE_OP_WRITE] = "store", + [PERF_COUNT_HW_CACHE_OP_PREFETCH] = "prefetch", +}; + +const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [PERF_COUNT_HW_CACHE_RESULT_ACCESS] = "refs", + [PERF_COUNT_HW_CACHE_RESULT_MISS] = "misses", }; +#define perf_event_name(array, id) ({ \ + const char *event_str = NULL; \ + \ + if ((id) < ARRAY_SIZE(array)) \ + event_str = array[id]; \ + event_str; \ +}) + static int link_parse_fd(int *argc, char ***argv) { + int fd; + if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -35,7 +105,10 @@ static int link_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return bpf_link_get_fd_by_id(id); + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) + p_err("failed to get link with ID %d: %s", id, strerror(errno)); + return fd; } else if (is_prefix(**argv, "pinned")) { char *path; @@ -54,9 +127,12 @@ static int link_parse_fd(int *argc, char ***argv) static void show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) { + const char *link_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - jsonw_string_field(wtr, "type", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + jsonw_string_field(wtr, "type", link_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -65,13 +141,97 @@ show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(wtr, "attach_type", - attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + jsonw_string_field(wtr, "attach_type", attach_type_str); else jsonw_uint_field(wtr, "attach_type", attach_type); } +static void show_link_ifindex_json(__u32 ifindex, json_writer_t *wtr) +{ + char devname[IF_NAMESIZE] = "(unknown)"; + + if (ifindex) + if_indextoname(ifindex, devname); + else + snprintf(devname, sizeof(devname), "(detached)"); + jsonw_string_field(wtr, "devname", devname); + jsonw_uint_field(wtr, "ifindex", ifindex); +} + +static bool is_iter_map_target(const char *target_name) +{ + return strcmp(target_name, "bpf_map_elem") == 0 || + strcmp(target_name, "bpf_sk_storage_map") == 0; +} + +static bool is_iter_cgroup_target(const char *target_name) +{ + return strcmp(target_name, "cgroup") == 0; +} + +static const char *cgroup_order_string(__u32 order) +{ + switch (order) { + case BPF_CGROUP_ITER_ORDER_UNSPEC: + return "order_unspec"; + case BPF_CGROUP_ITER_SELF_ONLY: + return "self_only"; + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + return "descendants_pre"; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + return "descendants_post"; + case BPF_CGROUP_ITER_ANCESTORS_UP: + return "ancestors_up"; + default: /* won't happen */ + return "unknown"; + } +} + +static bool is_iter_task_target(const char *target_name) +{ + return strcmp(target_name, "task") == 0 || + strcmp(target_name, "task_file") == 0 || + strcmp(target_name, "task_vma") == 0; +} + +static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + jsonw_string_field(wtr, "target_name", target_name); + + if (is_iter_map_target(target_name)) + jsonw_uint_field(wtr, "map_id", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + jsonw_uint_field(wtr, "tid", info->iter.task.tid); + else if (info->iter.task.pid) + jsonw_uint_field(wtr, "pid", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + jsonw_lluint_field(wtr, "cgroup_id", info->iter.cgroup.cgroup_id); + jsonw_string_field(wtr, "order", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(json_wtr, "pf", + info->netfilter.pf); + jsonw_uint_field(json_wtr, "hook", + info->netfilter.hooknum); + jsonw_int_field(json_wtr, "prio", + info->netfilter.priority); + jsonw_uint_field(json_wtr, "flags", + info->netfilter.flags); +} + static int get_prog_info(int prog_id, struct bpf_prog_info *info) { __u32 len = sizeof(*info); @@ -82,16 +242,238 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info) return prog_fd; memset(info, 0, sizeof(*info)); - err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + err = bpf_prog_get_info_by_fd(prog_fd, info, &len); if (err) p_err("can't get prog info: %s", strerror(errno)); close(prog_fd); return err; } +struct addr_cookie { + __u64 addr; + __u64 cookie; +}; + +static int cmp_addr_cookie(const void *A, const void *B) +{ + const struct addr_cookie *a = A, *b = B; + + if (a->addr == b->addr) + return 0; + return a->addr < b->addr ? -1 : 1; +} + +static struct addr_cookie * +get_addr_cookie_array(__u64 *addrs, __u64 *cookies, __u32 count) +{ + struct addr_cookie *data; + __u32 i; + + data = calloc(count, sizeof(data[0])); + if (!data) { + p_err("mem alloc failed"); + return NULL; + } + for (i = 0; i < count; i++) { + data[i].addr = addrs[i]; + data[i].cookie = cookies[i]; + } + qsort(data, count, sizeof(data[0]), cmp_addr_cookie); + return data; +} + +static void +show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + struct addr_cookie *data; + __u32 i, j = 0; + + jsonw_bool_field(json_wtr, "retprobe", + info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN); + jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count); + jsonw_uint_field(json_wtr, "missed", info->kprobe_multi.missed); + jsonw_name(json_wtr, "funcs"); + jsonw_start_array(json_wtr); + data = get_addr_cookie_array(u64_to_ptr(info->kprobe_multi.addrs), + u64_to_ptr(info->kprobe_multi.cookies), + info->kprobe_multi.count); + if (!data) + return; + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + if (!dd.sym_count) + goto error; + + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != data[j].addr) + continue; + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address); + jsonw_string_field(json_wtr, "func", dd.sym_mapping[i].name); + /* Print null if it is vmlinux */ + if (dd.sym_mapping[i].module[0] == '\0') { + jsonw_name(json_wtr, "module"); + jsonw_null(json_wtr); + } else { + jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module); + } + jsonw_uint_field(json_wtr, "cookie", data[j].cookie); + jsonw_end_object(json_wtr); + if (j++ == info->kprobe_multi.count) + break; + } + jsonw_end_array(json_wtr); +error: + free(data); +} + +static __u64 *u64_to_arr(__u64 val) +{ + return (__u64 *) u64_to_ptr(val); +} + +static void +show_uprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u32 i; + + jsonw_bool_field(json_wtr, "retprobe", + info->uprobe_multi.flags & BPF_F_UPROBE_MULTI_RETURN); + jsonw_string_field(json_wtr, "path", (char *) u64_to_ptr(info->uprobe_multi.path)); + jsonw_uint_field(json_wtr, "func_cnt", info->uprobe_multi.count); + jsonw_int_field(json_wtr, "pid", (int) info->uprobe_multi.pid); + jsonw_name(json_wtr, "funcs"); + jsonw_start_array(json_wtr); + + for (i = 0; i < info->uprobe_multi.count; i++) { + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "offset", + u64_to_arr(info->uprobe_multi.offsets)[i]); + jsonw_uint_field(json_wtr, "ref_ctr_offset", + u64_to_arr(info->uprobe_multi.ref_ctr_offsets)[i]); + jsonw_uint_field(json_wtr, "cookie", + u64_to_arr(info->uprobe_multi.cookies)[i]); + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +static void +show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_KRETPROBE); + jsonw_uint_field(wtr, "addr", info->perf_event.kprobe.addr); + jsonw_string_field(wtr, "func", + u64_to_ptr(info->perf_event.kprobe.func_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset); + jsonw_uint_field(wtr, "missed", info->perf_event.kprobe.missed); + jsonw_uint_field(wtr, "cookie", info->perf_event.kprobe.cookie); +} + +static void +show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_URETPROBE); + jsonw_string_field(wtr, "file", + u64_to_ptr(info->perf_event.uprobe.file_name)); + jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset); + jsonw_uint_field(wtr, "cookie", info->perf_event.uprobe.cookie); +} + +static void +show_perf_event_tracepoint_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_string_field(wtr, "tracepoint", + u64_to_ptr(info->perf_event.tracepoint.tp_name)); + jsonw_uint_field(wtr, "cookie", info->perf_event.tracepoint.cookie); +} + +static char *perf_config_hw_cache_str(__u64 config) +{ + const char *hw_cache, *result, *op; + char *str = malloc(PERF_HW_CACHE_LEN); + + if (!str) { + p_err("mem alloc failed"); + return NULL; + } + + hw_cache = perf_event_name(evsel__hw_cache, config & 0xff); + if (hw_cache) + snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache); + else + snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff); + + op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff); + if (op) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s-", op); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld-", (config >> 8) & 0xff); + + result = perf_event_name(evsel__hw_cache_result, config >> 16); + if (result) + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%s", result); + else + snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), + "%lld", config >> 16); + return str; +} + +static const char *perf_config_str(__u32 type, __u64 config) +{ + const char *perf_config; + + switch (type) { + case PERF_TYPE_HARDWARE: + perf_config = perf_event_name(event_symbols_hw, config); + break; + case PERF_TYPE_SOFTWARE: + perf_config = perf_event_name(event_symbols_sw, config); + break; + case PERF_TYPE_HW_CACHE: + perf_config = perf_config_hw_cache_str(config); + break; + default: + perf_config = NULL; + break; + } + return perf_config; +} + +static void +show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + jsonw_string_field(wtr, "event_type", perf_type); + else + jsonw_uint_field(wtr, "event_type", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + jsonw_string_field(wtr, "event_config", perf_config); + else + jsonw_uint_field(wtr, "event_config", config); + + jsonw_uint_field(wtr, "cookie", info->perf_event.event.cookie); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); +} + static int show_link_close_json(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; jsonw_start_object(json_wtr); @@ -101,48 +483,98 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: jsonw_string_field(json_wtr, "tp_name", - (const char *)info->raw_tracepoint.tp_name); + u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); if (err) return err; - if (prog_info.type < ARRAY_SIZE(prog_type_name)) - jsonw_string_field(json_wtr, "prog_type", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + jsonw_string_field(json_wtr, "prog_type", prog_type_str); else - jsonw_uint_field(json_wtr, "prog_type", - prog_info.type); + jsonw_uint_field(json_wtr, "prog_type", prog_info.type); show_link_attach_type_json(info->tracing.attach_type, json_wtr); + jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id); + jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: jsonw_lluint_field(json_wtr, "cgroup_id", info->cgroup.cgroup_id); show_link_attach_type_json(info->cgroup.attach_type, json_wtr); break; + case BPF_LINK_TYPE_ITER: + show_iter_json(info, json_wtr); + break; case BPF_LINK_TYPE_NETNS: jsonw_uint_field(json_wtr, "netns_ino", info->netns.netns_ino); show_link_attach_type_json(info->netns.attach_type, json_wtr); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_json(info, json_wtr); + break; + case BPF_LINK_TYPE_TCX: + show_link_ifindex_json(info->tcx.ifindex, json_wtr); + show_link_attach_type_json(info->tcx.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_NETKIT: + show_link_ifindex_json(info->netkit.ifindex, json_wtr); + show_link_attach_type_json(info->netkit.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_XDP: + show_link_ifindex_json(info->xdp.ifindex, json_wtr); + break; + case BPF_LINK_TYPE_STRUCT_OPS: + jsonw_uint_field(json_wtr, "map_id", + info->struct_ops.map_id); + break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_json(info, json_wtr); + break; + case BPF_LINK_TYPE_UPROBE_MULTI: + show_uprobe_multi_json(info, json_wtr); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_json(info, json_wtr); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_json(info, json_wtr); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_json(info, json_wtr); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_json(info, json_wtr); + break; + default: + break; + } + break; default: break; } - if (!hash_empty(link_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(link_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(link_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } + + emit_obj_refs_json(refs_table, info->id, json_wtr); + jsonw_end_object(json_wtr); return 0; @@ -150,26 +582,288 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) static void show_link_header_plain(struct bpf_link_info *info) { + const char *link_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - printf("%s ", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + printf("%s ", link_type_str); else printf("type %u ", info->type); - printf("prog %u ", info->prog_id); + if (info->type == BPF_LINK_TYPE_STRUCT_OPS) + printf("map %u ", info->struct_ops.map_id); + else + printf("prog %u ", info->prog_id); } static void show_link_attach_type_plain(__u32 attach_type) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("attach_type %s ", attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + printf("attach_type %s ", attach_type_str); else printf("attach_type %u ", attach_type); } +static void show_link_ifindex_plain(__u32 ifindex) +{ + char devname[IF_NAMESIZE * 2] = "(unknown)"; + char tmpname[IF_NAMESIZE]; + char *ret = NULL; + + if (ifindex) + ret = if_indextoname(ifindex, tmpname); + else + snprintf(devname, sizeof(devname), "(detached)"); + if (ret) + snprintf(devname, sizeof(devname), "%s(%d)", + tmpname, ifindex); + printf("ifindex %s ", devname); +} + +static void show_iter_plain(struct bpf_link_info *info) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + printf("target_name %s ", target_name); + + if (is_iter_map_target(target_name)) + printf("map_id %u ", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + printf("tid %u ", info->iter.task.tid); + else if (info->iter.task.pid) + printf("pid %u ", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + printf("cgroup_id %llu ", info->iter.cgroup.cgroup_id); + printf("order %s ", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +static const char * const pf2name[] = { + [NFPROTO_INET] = "inet", + [NFPROTO_IPV4] = "ip", + [NFPROTO_ARP] = "arp", + [NFPROTO_NETDEV] = "netdev", + [NFPROTO_BRIDGE] = "bridge", + [NFPROTO_IPV6] = "ip6", +}; + +static const char * const inethook2name[] = { + [NF_INET_PRE_ROUTING] = "prerouting", + [NF_INET_LOCAL_IN] = "input", + [NF_INET_FORWARD] = "forward", + [NF_INET_LOCAL_OUT] = "output", + [NF_INET_POST_ROUTING] = "postrouting", +}; + +static const char * const arphook2name[] = { + [NF_ARP_IN] = "input", + [NF_ARP_OUT] = "output", +}; + +void netfilter_dump_plain(const struct bpf_link_info *info) +{ + const char *hookname = NULL, *pfname = NULL; + unsigned int hook = info->netfilter.hooknum; + unsigned int pf = info->netfilter.pf; + + if (pf < ARRAY_SIZE(pf2name)) + pfname = pf2name[pf]; + + switch (pf) { + case NFPROTO_BRIDGE: /* bridge shares numbers with enum nf_inet_hooks */ + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + if (hook < ARRAY_SIZE(inethook2name)) + hookname = inethook2name[hook]; + break; + case NFPROTO_ARP: + if (hook < ARRAY_SIZE(arphook2name)) + hookname = arphook2name[hook]; + default: + break; + } + + if (pfname) + printf("\n\t%s", pfname); + else + printf("\n\tpf: %d", pf); + + if (hookname) + printf(" %s", hookname); + else + printf(", hook %u,", hook); + + printf(" prio %d", info->netfilter.priority); + + if (info->netfilter.flags) + printf(" flags 0x%x", info->netfilter.flags); +} + +static void show_kprobe_multi_plain(struct bpf_link_info *info) +{ + struct addr_cookie *data; + __u32 i, j = 0; + + if (!info->kprobe_multi.count) + return; + + if (info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN) + printf("\n\tkretprobe.multi "); + else + printf("\n\tkprobe.multi "); + printf("func_cnt %u ", info->kprobe_multi.count); + if (info->kprobe_multi.missed) + printf("missed %llu ", info->kprobe_multi.missed); + data = get_addr_cookie_array(u64_to_ptr(info->kprobe_multi.addrs), + u64_to_ptr(info->kprobe_multi.cookies), + info->kprobe_multi.count); + if (!data) + return; + + /* Load it once for all. */ + if (!dd.sym_count) + kernel_syms_load(&dd); + if (!dd.sym_count) + goto error; + + printf("\n\t%-16s %-16s %s", "addr", "cookie", "func [module]"); + for (i = 0; i < dd.sym_count; i++) { + if (dd.sym_mapping[i].address != data[j].addr) + continue; + printf("\n\t%016lx %-16llx %s", + dd.sym_mapping[i].address, data[j].cookie, dd.sym_mapping[i].name); + if (dd.sym_mapping[i].module[0] != '\0') + printf(" [%s] ", dd.sym_mapping[i].module); + else + printf(" "); + + if (j++ == info->kprobe_multi.count) + break; + } +error: + free(data); +} + +static void show_uprobe_multi_plain(struct bpf_link_info *info) +{ + __u32 i; + + if (!info->uprobe_multi.count) + return; + + if (info->uprobe_multi.flags & BPF_F_UPROBE_MULTI_RETURN) + printf("\n\turetprobe.multi "); + else + printf("\n\tuprobe.multi "); + + printf("path %s ", (char *) u64_to_ptr(info->uprobe_multi.path)); + printf("func_cnt %u ", info->uprobe_multi.count); + + if (info->uprobe_multi.pid) + printf("pid %d ", info->uprobe_multi.pid); + + printf("\n\t%-16s %-16s %-16s", "offset", "ref_ctr_offset", "cookies"); + for (i = 0; i < info->uprobe_multi.count; i++) { + printf("\n\t0x%-16llx 0x%-16llx 0x%-16llx", + u64_to_arr(info->uprobe_multi.offsets)[i], + u64_to_arr(info->uprobe_multi.ref_ctr_offsets)[i], + u64_to_arr(info->uprobe_multi.cookies)[i]); + } +} + +static void show_perf_event_kprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.kprobe.func_name); + if (buf[0] == '\0' && !info->perf_event.kprobe.addr) + return; + + if (info->perf_event.type == BPF_PERF_EVENT_KRETPROBE) + printf("\n\tkretprobe "); + else + printf("\n\tkprobe "); + if (info->perf_event.kprobe.addr) + printf("%llx ", info->perf_event.kprobe.addr); + printf("%s", buf); + if (info->perf_event.kprobe.offset) + printf("+%#x", info->perf_event.kprobe.offset); + if (info->perf_event.kprobe.missed) + printf(" missed %llu", info->perf_event.kprobe.missed); + if (info->perf_event.kprobe.cookie) + printf(" cookie %llu", info->perf_event.kprobe.cookie); + printf(" "); +} + +static void show_perf_event_uprobe_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.uprobe.file_name); + if (buf[0] == '\0') + return; + + if (info->perf_event.type == BPF_PERF_EVENT_URETPROBE) + printf("\n\turetprobe "); + else + printf("\n\tuprobe "); + printf("%s+%#x ", buf, info->perf_event.uprobe.offset); + if (info->perf_event.uprobe.cookie) + printf("cookie %llu ", info->perf_event.uprobe.cookie); +} + +static void show_perf_event_tracepoint_plain(struct bpf_link_info *info) +{ + const char *buf; + + buf = u64_to_ptr(info->perf_event.tracepoint.tp_name); + if (buf[0] == '\0') + return; + + printf("\n\ttracepoint %s ", buf); + if (info->perf_event.tracepoint.cookie) + printf("cookie %llu ", info->perf_event.tracepoint.cookie); +} + +static void show_perf_event_event_plain(struct bpf_link_info *info) +{ + __u64 config = info->perf_event.event.config; + __u32 type = info->perf_event.event.type; + const char *perf_type, *perf_config; + + printf("\n\tevent "); + perf_type = perf_event_name(perf_type_name, type); + if (perf_type) + printf("%s:", perf_type); + else + printf("%u :", type); + + perf_config = perf_config_str(type, config); + if (perf_config) + printf("%s ", perf_config); + else + printf("%llu ", config); + + if (info->perf_event.event.cookie) + printf("cookie %llu ", info->perf_event.event.cookie); + + if (type == PERF_TYPE_HW_CACHE && perf_config) + free((void *)perf_config); +} + static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; show_link_header_plain(info); @@ -177,41 +871,91 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: printf("\n\ttp '%s' ", - (const char *)info->raw_tracepoint.tp_name); + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); if (err) return err; - if (prog_info.type < ARRAY_SIZE(prog_type_name)) - printf("\n\tprog_type %s ", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + printf("\n\tprog_type %s ", prog_type_str); else printf("\n\tprog_type %u ", prog_info.type); show_link_attach_type_plain(info->tracing.attach_type); + if (info->tracing.target_obj_id || info->tracing.target_btf_id) + printf("\n\ttarget_obj_id %u target_btf_id %u ", + info->tracing.target_obj_id, + info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); show_link_attach_type_plain(info->cgroup.attach_type); break; + case BPF_LINK_TYPE_ITER: + show_iter_plain(info); + break; case BPF_LINK_TYPE_NETNS: printf("\n\tnetns_ino %u ", info->netns.netns_ino); show_link_attach_type_plain(info->netns.attach_type); break; + case BPF_LINK_TYPE_NETFILTER: + netfilter_dump_plain(info); + break; + case BPF_LINK_TYPE_TCX: + printf("\n\t"); + show_link_ifindex_plain(info->tcx.ifindex); + show_link_attach_type_plain(info->tcx.attach_type); + break; + case BPF_LINK_TYPE_NETKIT: + printf("\n\t"); + show_link_ifindex_plain(info->netkit.ifindex); + show_link_attach_type_plain(info->netkit.attach_type); + break; + case BPF_LINK_TYPE_XDP: + printf("\n\t"); + show_link_ifindex_plain(info->xdp.ifindex); + break; + case BPF_LINK_TYPE_KPROBE_MULTI: + show_kprobe_multi_plain(info); + break; + case BPF_LINK_TYPE_UPROBE_MULTI: + show_uprobe_multi_plain(info); + break; + case BPF_LINK_TYPE_PERF_EVENT: + switch (info->perf_event.type) { + case BPF_PERF_EVENT_EVENT: + show_perf_event_event_plain(info); + break; + case BPF_PERF_EVENT_TRACEPOINT: + show_perf_event_tracepoint_plain(info); + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + show_perf_event_kprobe_plain(info); + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + show_perf_event_uprobe_plain(info); + break; + default: + break; + } + break; default: break; } - if (!hash_empty(link_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(link_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(link_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); printf("\n"); @@ -220,14 +964,19 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) static int do_show_link(int fd) { + __u64 *ref_ctr_offsets = NULL, *offsets = NULL, *cookies = NULL; struct bpf_link_info info; __u32 len = sizeof(info); - char raw_tp_name[256]; + char path_buf[PATH_MAX]; + __u64 *addrs = NULL; + char buf[PATH_MAX]; + int count; int err; memset(&info, 0, sizeof(info)); + buf[0] = '\0'; again: - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_link_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get link info: %s", strerror(errno)); @@ -236,16 +985,110 @@ again: } if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && !info.raw_tracepoint.tp_name) { - info.raw_tracepoint.tp_name = (unsigned long)&raw_tp_name; - info.raw_tracepoint.tp_name_len = sizeof(raw_tp_name); + info.raw_tracepoint.tp_name = ptr_to_u64(&buf); + info.raw_tracepoint.tp_name_len = sizeof(buf); + goto again; + } + if (info.type == BPF_LINK_TYPE_ITER && + !info.iter.target_name) { + info.iter.target_name = ptr_to_u64(&buf); + info.iter.target_name_len = sizeof(buf); goto again; } + if (info.type == BPF_LINK_TYPE_KPROBE_MULTI && + !info.kprobe_multi.addrs) { + count = info.kprobe_multi.count; + if (count) { + addrs = calloc(count, sizeof(__u64)); + if (!addrs) { + p_err("mem alloc failed"); + close(fd); + return -ENOMEM; + } + info.kprobe_multi.addrs = ptr_to_u64(addrs); + cookies = calloc(count, sizeof(__u64)); + if (!cookies) { + p_err("mem alloc failed"); + free(addrs); + close(fd); + return -ENOMEM; + } + info.kprobe_multi.cookies = ptr_to_u64(cookies); + goto again; + } + } + if (info.type == BPF_LINK_TYPE_UPROBE_MULTI && + !info.uprobe_multi.offsets) { + count = info.uprobe_multi.count; + if (count) { + offsets = calloc(count, sizeof(__u64)); + if (!offsets) { + p_err("mem alloc failed"); + close(fd); + return -ENOMEM; + } + info.uprobe_multi.offsets = ptr_to_u64(offsets); + ref_ctr_offsets = calloc(count, sizeof(__u64)); + if (!ref_ctr_offsets) { + p_err("mem alloc failed"); + free(offsets); + close(fd); + return -ENOMEM; + } + info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets); + cookies = calloc(count, sizeof(__u64)); + if (!cookies) { + p_err("mem alloc failed"); + free(ref_ctr_offsets); + free(offsets); + close(fd); + return -ENOMEM; + } + info.uprobe_multi.cookies = ptr_to_u64(cookies); + info.uprobe_multi.path = ptr_to_u64(path_buf); + info.uprobe_multi.path_size = sizeof(path_buf); + goto again; + } + } + if (info.type == BPF_LINK_TYPE_PERF_EVENT) { + switch (info.perf_event.type) { + case BPF_PERF_EVENT_TRACEPOINT: + if (!info.perf_event.tracepoint.tp_name) { + info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); + info.perf_event.tracepoint.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_KPROBE: + case BPF_PERF_EVENT_KRETPROBE: + if (!info.perf_event.kprobe.func_name) { + info.perf_event.kprobe.func_name = ptr_to_u64(&buf); + info.perf_event.kprobe.name_len = sizeof(buf); + goto again; + } + break; + case BPF_PERF_EVENT_UPROBE: + case BPF_PERF_EVENT_URETPROBE: + if (!info.perf_event.uprobe.file_name) { + info.perf_event.uprobe.file_name = ptr_to_u64(&buf); + info.perf_event.uprobe.name_len = sizeof(buf); + goto again; + } + break; + default: + break; + } + } if (json_output) show_link_close_json(fd, &info); else show_link_close_plain(fd, &info); + free(ref_ctr_offsets); + free(cookies); + free(offsets); + free(addrs); close(fd); return 0; } @@ -255,14 +1098,23 @@ static int do_show(int argc, char **argv) __u32 id = 0; int err, fd; - if (show_pinned) - build_pinned_obj_table(&link_table, BPF_OBJ_LINK); + if (show_pinned) { + link_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(link_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(link_table, BPF_OBJ_LINK); + } + build_obj_refs_table(&refs_table, BPF_OBJ_LINK); if (argc == 2) { fd = link_parse_fd(&argc, &argv); if (fd < 0) return fd; - return do_show_link(fd); + do_show_link(fd); + goto out; } if (argc) @@ -296,6 +1148,14 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(link_table); + +out: + if (dd.sym_count) + kernel_syms_destroy(&dd); return errno == ENOENT ? 0 : -1; } @@ -309,6 +1169,34 @@ static int do_pin(int argc, char **argv) return err; } +static int do_detach(int argc, char **argv) +{ + int err, fd; + + if (argc != 2) { + p_err("link specifier is invalid or missing\n"); + return 1; + } + + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return 1; + + err = bpf_link_detach(fd); + if (err) + err = -errno; + close(fd); + if (err) { + p_err("failed link detach: %s", strerror(-err)); + return 1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -319,10 +1207,12 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [LINK]\n" " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s detach LINK\n" " %1$s %2$s help\n" "\n" " " HELP_SPEC_LINK "\n" - " " HELP_SPEC_OPTIONS "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" "", bin_name, argv[-2]); @@ -334,6 +1224,7 @@ static const struct cmd cmds[] = { { "list", do_show }, { "help", do_help }, { "pin", do_pin }, + { "detach", do_detach }, { 0 } }; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 46bd716a9d86..08d0ac543c67 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -10,6 +10,8 @@ #include <string.h> #include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> #include <bpf/libbpf.h> #include "main.h" @@ -28,9 +30,9 @@ bool show_pinned; bool block_mount; bool verifier_logs; bool relaxed_maps; -struct pinned_obj_table prog_table; -struct pinned_obj_table map_table; -struct pinned_obj_table link_table; +bool use_loader; +struct btf *base_btf; +struct hashmap *refs_table; static void __noreturn clean_and_exit(int i) { @@ -60,22 +62,124 @@ static int do_help(int argc, char **argv) " %s version\n" "\n" " OBJECT := { prog | map | link | cgroup | perf | net | feature | btf | gen | struct_ops | iter }\n" - " " HELP_SPEC_OPTIONS "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-V|--version} }\n" "", bin_name, bin_name, bin_name); return 0; } +static int do_batch(int argc, char **argv); +static int do_version(int argc, char **argv); + +static const struct cmd commands[] = { + { "help", do_help }, + { "batch", do_batch }, + { "prog", do_prog }, + { "map", do_map }, + { "link", do_link }, + { "cgroup", do_cgroup }, + { "perf", do_perf }, + { "net", do_net }, + { "feature", do_feature }, + { "btf", do_btf }, + { "gen", do_gen }, + { "struct_ops", do_struct_ops }, + { "iter", do_iter }, + { "version", do_version }, + { 0 } +}; + +#ifndef BPFTOOL_VERSION +/* bpftool's major and minor version numbers are aligned on libbpf's. There is + * an offset of 6 for the version number, because bpftool's version was higher + * than libbpf's when we adopted this scheme. The patch number remains at 0 + * for now. Set BPFTOOL_VERSION to override. + */ +#define BPFTOOL_MAJOR_VERSION (LIBBPF_MAJOR_VERSION + 6) +#define BPFTOOL_MINOR_VERSION LIBBPF_MINOR_VERSION +#define BPFTOOL_PATCH_VERSION 0 +#endif + +static void +print_feature(const char *feature, bool state, unsigned int *nb_features) +{ + if (state) { + printf("%s %s", *nb_features ? "," : "", feature); + *nb_features = *nb_features + 1; + } +} + static int do_version(int argc, char **argv) { +#ifdef HAVE_LIBBFD_SUPPORT + const bool has_libbfd = true; +#else + const bool has_libbfd = false; +#endif +#ifdef HAVE_LLVM_SUPPORT + const bool has_llvm = true; +#else + const bool has_llvm = false; +#endif +#ifdef BPFTOOL_WITHOUT_SKELETONS + const bool has_skeletons = false; +#else + const bool has_skeletons = true; +#endif + bool bootstrap = false; + int i; + + for (i = 0; commands[i].cmd; i++) { + if (!strcmp(commands[i].cmd, "prog")) { + /* Assume we run a bootstrap version if "bpftool prog" + * is not available. + */ + bootstrap = !commands[i].func; + break; + } + } + if (json_output) { - jsonw_start_object(json_wtr); + jsonw_start_object(json_wtr); /* root object */ + jsonw_name(json_wtr, "version"); +#ifdef BPFTOOL_VERSION jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION); - jsonw_end_object(json_wtr); +#else + jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + jsonw_name(json_wtr, "libbpf_version"); + jsonw_printf(json_wtr, "\"%d.%d\"", + libbpf_major_version(), libbpf_minor_version()); + + jsonw_name(json_wtr, "features"); + jsonw_start_object(json_wtr); /* features */ + jsonw_bool_field(json_wtr, "libbfd", has_libbfd); + jsonw_bool_field(json_wtr, "llvm", has_llvm); + jsonw_bool_field(json_wtr, "skeletons", has_skeletons); + jsonw_bool_field(json_wtr, "bootstrap", bootstrap); + jsonw_end_object(json_wtr); /* features */ + + jsonw_end_object(json_wtr); /* root object */ } else { + unsigned int nb_features = 0; + +#ifdef BPFTOOL_VERSION printf("%s v%s\n", bin_name, BPFTOOL_VERSION); +#else + printf("%s v%d.%d.%d\n", bin_name, BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + printf("using libbpf %s\n", libbpf_version_string()); + printf("features:"); + print_feature("libbfd", has_libbfd, &nb_features); + print_feature("llvm", has_llvm, &nb_features); + print_feature("skeletons", has_skeletons, &nb_features); + print_feature("bootstrap", bootstrap, &nb_features); + printf("\n"); } return 0; } @@ -92,9 +196,16 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv, if (argc < 1 && cmds[0].func) return cmds[0].func(argc, argv); - for (i = 0; cmds[i].func; i++) - if (is_prefix(*argv, cmds[i].cmd)) + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not supported in bootstrap mode", + cmds[i].cmd); + return -1; + } return cmds[i].func(argc - 1, argv + 1); + } + } help(argc - 1, argv + 1); @@ -209,26 +320,6 @@ static int make_args(char *line, char *n_argv[], int maxargs, int cmd_nb) return n_argc; } -static int do_batch(int argc, char **argv); - -static const struct cmd cmds[] = { - { "help", do_help }, - { "batch", do_batch }, - { "prog", do_prog }, - { "map", do_map }, - { "link", do_link }, - { "cgroup", do_cgroup }, - { "perf", do_perf }, - { "net", do_net }, - { "feature", do_feature }, - { "btf", do_btf }, - { "gen", do_gen }, - { "struct_ops", do_struct_ops }, - { "iter", do_iter }, - { "version", do_version }, - { 0 } -}; - static int do_batch(int argc, char **argv) { char buf[BATCH_LINE_LEN_MAX], contline[BATCH_LINE_LEN_MAX]; @@ -237,18 +328,18 @@ static int do_batch(int argc, char **argv) int n_argc; FILE *fp; char *cp; - int err; + int err = 0; int i; if (argc < 2) { p_err("too few parameters for batch"); return -1; - } else if (!is_prefix(*argv, "file")) { - p_err("expected 'file', got: %s", *argv); - return -1; } else if (argc > 2) { p_err("too many parameters for batch"); return -1; + } else if (!is_prefix(*argv, "file")) { + p_err("expected 'file', got: %s", *argv); + return -1; } NEXT_ARG(); @@ -301,8 +392,10 @@ static int do_batch(int argc, char **argv) n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines); if (!n_argc) continue; - if (n_argc < 0) + if (n_argc < 0) { + err = n_argc; goto err_close; + } if (json_output) { jsonw_start_object(json_wtr); @@ -314,7 +407,7 @@ static int do_batch(int argc, char **argv) jsonw_name(json_wtr, "output"); } - err = cmd_select(cmds, n_argc, n_argv, do_help); + err = cmd_select(commands, n_argc, n_argv, do_help); if (json_output) jsonw_end_object(json_wtr); @@ -331,7 +424,6 @@ static int do_batch(int argc, char **argv) } else { if (!json_output) printf("processed %d commands\n", lines); - err = 0; } err_close: if (fp != stdin) @@ -354,27 +446,39 @@ int main(int argc, char **argv) { "mapcompat", no_argument, NULL, 'm' }, { "nomount", no_argument, NULL, 'n' }, { "debug", no_argument, NULL, 'd' }, + { "use-loader", no_argument, NULL, 'L' }, + { "base-btf", required_argument, NULL, 'B' }, { 0 } }; + bool version_requested = false; int opt, ret; + setlinebuf(stdout); + +#ifdef USE_LIBCAP + /* Libcap < 2.63 hooks before main() to compute the number of + * capabilities of the running kernel, and doing so it calls prctl() + * which may fail and set errno to non-zero. + * Let's reset errno to make sure this does not interfere with the + * batch mode. + */ + errno = 0; +#endif + last_do_help = do_help; pretty_output = false; json_output = false; show_pinned = false; block_mount = false; - bin_name = argv[0]; - - hash_init(prog_table.table); - hash_init(map_table.table); - hash_init(link_table.table); + bin_name = "bpftool"; opterr = 0; - while ((opt = getopt_long(argc, argv, "Vhpjfmnd", + while ((opt = getopt_long(argc, argv, "VhpjfLmndB:l", options, NULL)) >= 0) { switch (opt) { case 'V': - return do_version(argc, argv); + version_requested = true; + break; case 'h': return do_help(argc, argv); case 'p': @@ -404,6 +508,17 @@ int main(int argc, char **argv) libbpf_set_print(print_all_levels); verifier_logs = true; break; + case 'B': + base_btf = btf__parse(optarg, NULL); + if (!base_btf) { + p_err("failed to parse base BTF at '%s': %d\n", + optarg, -errno); + return -1; + } + break; + case 'L': + use_loader = true; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) @@ -418,16 +533,15 @@ int main(int argc, char **argv) if (argc < 0) usage(); - ret = cmd_select(cmds, argc, argv, do_help); + if (version_requested) + return do_version(argc, argv); + + ret = cmd_select(commands, argc, argv, do_help); if (json_output) jsonw_destroy(&json_wtr); - if (show_pinned) { - delete_pinned_obj_table(&prog_table); - delete_pinned_obj_table(&map_table); - delete_pinned_obj_table(&link_table); - } + btf__free(base_btf); return ret; } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 5cdf0bc049bd..b8bb08d10dec 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -8,12 +8,12 @@ #undef GCC_VERSION #include <stdbool.h> #include <stdio.h> +#include <stdlib.h> #include <linux/bpf.h> #include <linux/compiler.h> #include <linux/kernel.h> -#include <linux/hashtable.h> -#include <tools/libc_compat.h> +#include <bpf/hashmap.h> #include <bpf/libbpf.h> #include "json_writer.h" @@ -21,7 +21,15 @@ /* Make sure we do not use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) @@ -49,89 +57,19 @@ #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ - "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \ - "\t {-m|--mapcompat} | {-n|--nomount} }" + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug}" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" #define HELP_SPEC_LINK \ "LINK := { id LINK_ID | pinned FILE }" -static const char * const prog_type_name[] = { - [BPF_PROG_TYPE_UNSPEC] = "unspec", - [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", - [BPF_PROG_TYPE_KPROBE] = "kprobe", - [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", - [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", - [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", - [BPF_PROG_TYPE_XDP] = "xdp", - [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", - [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", - [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", - [BPF_PROG_TYPE_LWT_IN] = "lwt_in", - [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", - [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", - [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_LWT_SEG6LOCAL] = "lwt_seg6local", - [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", - [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", - [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", - [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", - [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", - [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", - [BPF_PROG_TYPE_TRACING] = "tracing", - [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_PROG_TYPE_EXT] = "ext", -}; - -static const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [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_INET4_GETPEERNAME] = "getpeername4", - [BPF_CGROUP_INET6_GETPEERNAME] = "getpeername6", - [BPF_CGROUP_INET4_GETSOCKNAME] = "getsockname4", - [BPF_CGROUP_INET6_GETSOCKNAME] = "getsockname6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", - [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", - [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", - [BPF_LIRC_MODE2] = "lirc_mode2", - [BPF_FLOW_DISSECTOR] = "flow_dissector", - [BPF_TRACE_RAW_TP] = "raw_tp", - [BPF_TRACE_FENTRY] = "fentry", - [BPF_TRACE_FEXIT] = "fexit", - [BPF_MODIFY_RETURN] = "mod_ret", - [BPF_LSM_MAC] = "lsm_mac", -}; - -extern const char * const map_type_name[]; -extern const size_t map_type_name_size; - +/* keep in sync with the definition in skeleton/pid_iter.bpf.c */ enum bpf_obj_type { BPF_OBJ_UNKNOWN, BPF_OBJ_PROG, BPF_OBJ_MAP, BPF_OBJ_LINK, + BPF_OBJ_BTF, }; extern const char *bin_name; @@ -139,12 +77,13 @@ extern const char *bin_name; extern json_writer_t *json_wtr; extern bool json_output; extern bool show_pinned; +extern bool show_pids; extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; -extern struct pinned_obj_table prog_table; -extern struct pinned_obj_table map_table; -extern struct pinned_obj_table link_table; +extern bool use_loader; +extern struct btf *base_btf; +extern struct hashmap *refs_table; void __printf(1, 2) p_err(const char *fmt, ...); void __printf(1, 2) p_info(const char *fmt, ...); @@ -158,22 +97,31 @@ void set_max_rlimit(void); int mount_tracefs(const char *target); -struct pinned_obj_table { - DECLARE_HASHTABLE(table, 16); +struct obj_ref { + int pid; + char comm[16]; }; -struct pinned_obj { - __u32 id; - char *path; - struct hlist_node hash; +struct obj_refs { + int ref_cnt; + bool has_bpf_cookie; + struct obj_ref *refs; + __u64 bpf_cookie; }; struct btf; struct bpf_line_info; -int build_pinned_obj_table(struct pinned_obj_table *table, +int build_pinned_obj_table(struct hashmap *table, enum bpf_obj_type type); -void delete_pinned_obj_table(struct pinned_obj_table *tab); +void delete_pinned_obj_table(struct hashmap *table); +__weak int build_obj_refs_table(struct hashmap **table, + enum bpf_obj_type type); +__weak void delete_obj_refs_table(struct hashmap *table); +__weak void emit_obj_refs_json(struct hashmap *table, __u32 id, + json_writer_t *json_wtr); +__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id, + const char *prefix); void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); @@ -185,56 +133,67 @@ struct cmd { int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)); +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); -int open_obj_pinned(char *path, bool quiet); -int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name); +int open_obj_pinned(const char *path, bool quiet); +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); +int mount_bpffs_for_pin(const char *name, bool is_dir); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); 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_link(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 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); +/* commands available in bootstrap mode */ int do_gen(int argc, char **argv); -int do_struct_ops(int argc, char **argv); -int do_iter(int argc, char **argv); +int do_btf(int argc, char **argv); + +/* non-bootstrap only commands */ +int do_prog(int argc, char **arg) __weak; +int do_map(int argc, char **arg) __weak; +int do_link(int argc, char **arg) __weak; +int do_event_pipe(int argc, char **argv) __weak; +int do_cgroup(int argc, char **arg) __weak; +int do_perf(int argc, char **arg) __weak; +int do_net(int argc, char **arg) __weak; +int do_tracelog(int argc, char **arg) __weak; +int do_feature(int argc, char **argv) __weak; +int do_struct_ops(int argc, char **argv) __weak; +int do_iter(int argc, char **argv) __weak; int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); +int prog_parse_fds(int *argc, char ***argv, int **fds); int map_parse_fd(int *argc, char ***argv); -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); +int map_parse_fds(int *argc, char ***argv, int **fds); +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len); struct bpf_prog_linfo; -#ifdef HAVE_LIBBFD_SUPPORT -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum); +#if defined(HAVE_LLVM_SUPPORT) || defined(HAVE_LIBBFD_SUPPORT) +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum); int disasm_init(void); #else static inline -void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch, const char *disassembler_options, - const struct btf *btf, - const struct bpf_prog_linfo *prog_linfo, - __u64 func_ksym, unsigned int func_idx, - bool linum) +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) { + return 0; } static inline int disasm_init(void) { - p_err("No libbfd support"); + p_err("No JIT disassembly support"); return -1; } #endif @@ -244,8 +203,7 @@ void print_hex_data_json(uint8_t *data, size_t len); unsigned int get_page_size(void); unsigned int get_possible_cpus(void); const char * -ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, - const char **opt); +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt); struct btf_dumper { const struct btf *btf; @@ -271,6 +229,8 @@ void btf_dump_linfo_plain(const struct btf *btf, const char *prefix, bool linum); void btf_dump_linfo_json(const struct btf *btf, const struct bpf_line_info *linfo, bool linum); +void btf_dump_linfo_dotlabel(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum); struct nlattr; struct ifinfomsg; @@ -281,4 +241,33 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, int print_all_levels(__maybe_unused enum libbpf_print_level level, const char *format, va_list args); + +size_t hash_fn_for_key_as_id(long key, void *ctx); +bool equal_fn_for_key_as_id(long k1, long k2, void *ctx); + +/* bpf_attach_type_input_str - convert the provided attach type value into a + * textual representation that we accept for input purposes. + * + * This function is similar in nature to libbpf_bpf_attach_type_str, but + * recognizes some attach type names that have been used by the program in the + * past and which do not follow the string inference scheme that libbpf uses. + * These textual representations should only be used for user input. + * + * @t: The attach type + * Returns a pointer to a static string identifying the attach type. NULL is + * returned for unknown bpf_attach_type values. + */ +const char *bpf_attach_type_input_str(enum bpf_attach_type t); + +static inline bool hashmap__empty(struct hashmap *map) +{ + return map ? hashmap__size(map) == 0 : true; +} + +int pathname_concat(char *buf, int buf_sz, const char *path, + const char *name); + +/* print netfilter bpf_link info */ +void netfilter_dump_plain(const struct bpf_link_info *info); +void netfilter_dump_json(const struct bpf_link_info *info, json_writer_t *wtr); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 1d3b60651078..b89bd792c1d5 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ -#include <assert.h> #include <errno.h> #include <fcntl.h> #include <linux/err.h> @@ -17,42 +16,12 @@ #include <bpf/bpf.h> #include <bpf/btf.h> +#include <bpf/hashmap.h> #include "json_writer.h" #include "main.h" -const char * const map_type_name[] = { - [BPF_MAP_TYPE_UNSPEC] = "unspec", - [BPF_MAP_TYPE_HASH] = "hash", - [BPF_MAP_TYPE_ARRAY] = "array", - [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", - [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", - [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", - [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", - [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", - [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", - [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", - [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", - [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", - [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", - [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", - [BPF_MAP_TYPE_DEVMAP] = "devmap", - [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", - [BPF_MAP_TYPE_SOCKMAP] = "sockmap", - [BPF_MAP_TYPE_CPUMAP] = "cpumap", - [BPF_MAP_TYPE_XSKMAP] = "xskmap", - [BPF_MAP_TYPE_SOCKHASH] = "sockhash", - [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", - [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", - [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", - [BPF_MAP_TYPE_QUEUE] = "queue", - [BPF_MAP_TYPE_STACK] = "stack", - [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", - [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_MAP_TYPE_RINGBUF] = "ringbuf", -}; - -const size_t map_type_name_size = ARRAY_SIZE(map_type_name); +static struct hashmap *map_table; static bool map_is_per_cpu(__u32 type) { @@ -75,12 +44,18 @@ static bool map_is_map_of_progs(__u32 type) static int map_type_from_str(const char *type) { + const char *map_type_str; unsigned int i; - for (i = 0; i < ARRAY_SIZE(map_type_name); i++) + for (i = 0; ; i++) { + map_type_str = libbpf_bpf_map_type_str(i); + if (!map_type_str) + break; + /* Don't allow prefixing in case of possible future shadowing */ - if (map_type_name[i] && !strcmp(map_type_name[i], type)) + if (!strcmp(map_type_str, type)) return i; + } return -1; } @@ -93,168 +68,12 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -static int map_fd_by_name(char *name, int **fds) -{ - unsigned int id = 0; - int fd, nb_fds = 0; - void *tmp; - int err; - - while (true) { - struct bpf_map_info info = {}; - __u32 len = sizeof(info); - - err = bpf_map_get_next_id(id, &id); - if (err) { - if (errno != ENOENT) { - p_err("%s", strerror(errno)); - goto err_close_fds; - } - return nb_fds; - } - - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) { - p_err("can't get map by id (%u): %s", - id, strerror(errno)); - goto err_close_fds; - } - - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err) { - p_err("can't get map info (%u): %s", - id, strerror(errno)); - goto err_close_fd; - } - - if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { - close(fd); - continue; - } - - if (nb_fds > 0) { - tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); - if (!tmp) { - p_err("failed to realloc"); - goto err_close_fd; - } - *fds = tmp; - } - (*fds)[nb_fds++] = fd; - } - -err_close_fd: - close(fd); -err_close_fds: - while (--nb_fds >= 0) - close((*fds)[nb_fds]); - return -1; -} - -static int map_parse_fds(int *argc, char ***argv, int **fds) -{ - if (is_prefix(**argv, "id")) { - unsigned int id; - char *endptr; - - NEXT_ARGP(); - - id = strtoul(**argv, &endptr, 0); - if (*endptr) { - p_err("can't parse %s as ID", **argv); - return -1; - } - NEXT_ARGP(); - - (*fds)[0] = bpf_map_get_fd_by_id(id); - if ((*fds)[0] < 0) { - p_err("get map by id (%u): %s", id, strerror(errno)); - return -1; - } - return 1; - } else if (is_prefix(**argv, "name")) { - char *name; - - NEXT_ARGP(); - - name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { - p_err("can't parse name"); - return -1; - } - NEXT_ARGP(); - - return map_fd_by_name(name, fds); - } else if (is_prefix(**argv, "pinned")) { - char *path; - - NEXT_ARGP(); - - path = **argv; - NEXT_ARGP(); - - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); - if ((*fds)[0] < 0) - return -1; - return 1; - } - - p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); - return -1; -} - -int map_parse_fd(int *argc, char ***argv) -{ - int *fds = NULL; - int nb_fds, fd; - - fds = malloc(sizeof(int)); - if (!fds) { - p_err("mem alloc failed"); - return -1; - } - nb_fds = map_parse_fds(argc, argv, &fds); - if (nb_fds != 1) { - if (nb_fds > 1) { - p_err("several maps match this handle"); - while (nb_fds--) - close(fds[nb_fds]); - } - fd = -1; - goto exit_free; - } - - fd = fds[0]; -exit_free: - free(fds); - return fd; -} - -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) -{ - int err; - int fd; - - fd = map_parse_fd(argc, argv); - if (fd < 0) - return -1; - - err = bpf_obj_get_info_by_fd(fd, info, info_len); - if (err) { - p_err("can't get map info: %s", strerror(errno)); - close(fd); - return err; - } - - return fd; -} - 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; + int ret = 0; /* start of key-value pair */ jsonw_start_object(d->jw); @@ -320,6 +139,9 @@ 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 (map_is_map_of_maps(info->type)) + jsonw_uint_field(json_wtr, "inner_map_id", + *(unsigned int *)value); if (btf) { struct btf_dumper d = { .btf = btf, @@ -368,8 +190,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_end_object(json_wtr); } -static void print_entry_error(struct bpf_map_info *info, unsigned char *key, - const char *error_msg) +static void +print_entry_error_msg(struct bpf_map_info *info, unsigned char *key, + const char *error_msg) { int msg_size = strlen(error_msg); bool single_line, break_names; @@ -387,6 +210,40 @@ static void print_entry_error(struct bpf_map_info *info, unsigned char *key, printf("\n"); } +static void +print_entry_error(struct bpf_map_info *map_info, void *key, int lookup_errno) +{ + /* For prog_array maps or arrays of maps, failure to lookup the value + * means there is no entry for that key. Do not print an error message + * in that case. + */ + if ((map_is_map_of_maps(map_info->type) || + map_is_map_of_progs(map_info->type)) && lookup_errno == ENOENT) + return; + + if (json_output) { + jsonw_start_object(json_wtr); /* entry */ + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, map_info->key_size); + jsonw_name(json_wtr, "value"); + jsonw_start_object(json_wtr); /* error */ + jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); + jsonw_end_object(json_wtr); /* error */ + jsonw_end_object(json_wtr); /* entry */ + } else { + const char *msg = NULL; + + if (lookup_errno == ENOENT) + msg = "<no entry>"; + else if (lookup_errno == ENOSPC && + map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + msg = "<cannot read>"; + + print_entry_error_msg(map_info, key, + msg ? : strerror(lookup_errno)); + } +} + static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, unsigned char *value) { @@ -405,8 +262,13 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { - printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (map_is_map_of_maps(info->type)) { + printf("inner_map_id:%c", break_names ? '\n' : ' '); + printf("%u ", *(unsigned int *)value); + } else { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } } printf("\n"); @@ -587,9 +449,12 @@ static int parse_elem(char **argv, struct bpf_map_info *info, static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) { + const char *map_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(wtr, "type", map_type_name[info->type]); + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + jsonw_string_field(wtr, "type", map_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -619,7 +484,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "max_entries", info->max_entries); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { @@ -628,10 +493,12 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < ARRAY_SIZE(prog_type_name)) + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) jsonw_string_field(json_wtr, "owner_prog_type", - prog_type_name[prog_type]); + prog_type_str); else jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); @@ -654,18 +521,18 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (info->btf_id) jsonw_int_field(json_wtr, "btf_id", info->btf_id); - if (!hash_empty(map_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(map_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(map_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } + emit_obj_refs_json(refs_table, info->id, json_wtr); + jsonw_end_object(json_wtr); return 0; @@ -673,9 +540,13 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) static void show_map_header_plain(struct bpf_map_info *info) { + const char *map_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - printf("%s ", map_type_name[info->type]); + + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + printf("%s ", map_type_str); else printf("type %u ", info->type); @@ -711,10 +582,11 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < ARRAY_SIZE(prog_type_name)) - printf("owner_prog_type %s ", - prog_type_name[prog_type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + printf("owner_prog_type %s ", prog_type_str); else printf("owner_prog_type %d ", prog_type); } @@ -727,25 +599,20 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) } close(fd); - if (!hash_empty(map_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(map_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(map_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } - printf("\n"); if (frozen_str) { frozen = atoi(frozen_str); free(frozen_str); } - if (!info->btf_id && !frozen) - return 0; - - printf("\t"); + if (info->btf_id || frozen) + printf("\n\t"); if (info->btf_id) printf("btf_id %d", info->btf_id); @@ -753,6 +620,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (frozen) printf("%sfrozen", info->btf_id ? " " : ""); + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + printf("\n"); return 0; } @@ -777,7 +646,7 @@ static int do_show_subset(int argc, char **argv) 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); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); @@ -809,8 +678,16 @@ static int do_show(int argc, char **argv) int err; int fd; - if (show_pinned) - build_pinned_obj_table(&map_table, BPF_OBJ_MAP); + if (show_pinned) { + map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(map_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(map_table, BPF_OBJ_MAP); + } + build_obj_refs_table(&refs_table, BPF_OBJ_MAP); if (argc == 2) return do_show_subset(argc, argv); @@ -839,7 +716,7 @@ static int do_show(int argc, char **argv) break; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -854,6 +731,11 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(map_table); + return errno == ENOENT ? 0 : -1; } @@ -861,56 +743,23 @@ static int dump_map_elem(int fd, void *key, void *value, struct bpf_map_info *map_info, struct btf *btf, json_writer_t *btf_wtr) { - int num_elems = 0; - int lookup_errno; - - if (!bpf_map_lookup_elem(fd, key, value)) { - if (json_output) { - print_entry_json(map_info, key, value, btf); - } else { - if (btf) { - struct btf_dumper d = { - .btf = btf, - .jw = btf_wtr, - .is_plain_text = true, - }; - - do_dump_btf(&d, map_info, key, value); - } else { - print_entry_plain(map_info, key, value); - } - num_elems++; - } - return num_elems; + if (bpf_map_lookup_elem(fd, key, value)) { + print_entry_error(map_info, key, errno); + return -1; } - /* lookup error handling */ - lookup_errno = errno; - - if (map_is_map_of_maps(map_info->type) || - map_is_map_of_progs(map_info->type)) - return 0; - if (json_output) { - jsonw_start_object(json_wtr); - jsonw_name(json_wtr, "key"); - print_hex_data_json(key, map_info->key_size); - jsonw_name(json_wtr, "value"); - jsonw_start_object(json_wtr); - jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); - jsonw_end_object(json_wtr); - jsonw_end_object(json_wtr); - } else { - const char *msg = NULL; - - if (lookup_errno == ENOENT) - msg = "<no entry>"; - else if (lookup_errno == ENOSPC && - map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) - msg = "<cannot read>"; + print_entry_json(map_info, key, value, btf); + } else if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; - print_entry_error(map_info, key, - msg ? : strerror(lookup_errno)); + do_dump_btf(&d, map_info, key, value); + } else { + print_entry_plain(map_info, key, value); } return 0; @@ -923,7 +772,7 @@ static int maps_have_btf(int *fds, int nb_fds) int err, i; for (i = 0; i < nb_fds; i++) { - err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); return -1; @@ -938,42 +787,38 @@ static int maps_have_btf(int *fds, int nb_fds) static struct btf *btf_vmlinux; -static struct btf *get_map_kv_btf(const struct bpf_map_info *info) +static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf) { - struct btf *btf = NULL; + int err = 0; if (info->btf_vmlinux_value_type_id) { if (!btf_vmlinux) { btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(btf_vmlinux)) + if (!btf_vmlinux) { p_err("failed to get kernel btf"); + return -errno; + } } - return btf_vmlinux; + *btf = btf_vmlinux; } else if (info->btf_value_type_id) { - int err; - - err = btf__get_from_id(info->btf_id, &btf); - if (err || !btf) { + *btf = btf__load_from_kernel_by_id(info->btf_id); + if (!*btf) { + err = -errno; p_err("failed to get btf"); - btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH); } + } else { + *btf = NULL; } - return btf; + return err; } static void free_map_kv_btf(struct btf *btf) { - if (!IS_ERR(btf) && btf != btf_vmlinux) + if (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) @@ -994,9 +839,8 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, prev_key = NULL; if (wtr) { - btf = get_map_kv_btf(info); - if (IS_ERR(btf)) { - err = PTR_ERR(btf); + err = get_map_kv_btf(info, &btf); + if (err) { goto exit_free; } @@ -1011,9 +855,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, } if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info->value_size != 8) + info->value_size != 8) { + const char *map_type_str; + + map_type_str = libbpf_bpf_map_type_str(info->type); p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info->type]); + map_type_str); + } while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -1021,7 +869,8 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, err = 0; break; } - num_elems += dump_map_elem(fd, key, value, info, btf, wtr); + if (!dump_map_elem(fd, key, value, info, btf, wtr)) + num_elems++; prev_key = key; } @@ -1084,7 +933,7 @@ static int do_dump(int argc, char **argv) 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)) { + if (bpf_map_get_info_by_fd(fds[i], &info, &len)) { p_err("can't get map info: %s", strerror(errno)); break; } @@ -1106,7 +955,7 @@ exit_close: close(fds[i]); exit_free: free(fds); - free_btf_vmlinux(); + btf__free(btf_vmlinux); return err; } @@ -1183,14 +1032,10 @@ static void print_key_value(struct bpf_map_info *info, void *key, void *value) { json_writer_t *btf_wtr; - struct btf *btf = NULL; - int err; + struct btf *btf; - err = btf__get_from_id(info->btf_id, &btf); - if (err) { - p_err("failed to get btf"); + if (get_map_kv_btf(info, &btf)) return; - } if (json_output) { print_entry_json(info, key, value, btf); @@ -1393,9 +1238,12 @@ static int do_pin(int argc, char **argv) static int do_create(int argc, char **argv) { - struct bpf_create_map_attr attr = { NULL, }; + LIBBPF_OPTS(bpf_map_create_opts, attr); + enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC; + __u32 key_size = 0, value_size = 0, max_entries = 0; + const char *map_name = NULL; const char *pinfile; - int err, fd; + int err = -1, fd; if (!REQ_ARGS(7)) return -1; @@ -1408,78 +1256,101 @@ static int do_create(int argc, char **argv) if (is_prefix(*argv, "type")) { NEXT_ARG(); - if (attr.map_type) { + if (map_type) { p_err("map type already specified"); - return -1; + goto exit; } - attr.map_type = map_type_from_str(*argv); - if ((int)attr.map_type < 0) { + map_type = map_type_from_str(*argv); + if ((int)map_type < 0) { p_err("unrecognized map type: %s", *argv); - return -1; + goto exit; } NEXT_ARG(); } else if (is_prefix(*argv, "name")) { NEXT_ARG(); - attr.name = GET_ARG(); + map_name = GET_ARG(); } else if (is_prefix(*argv, "key")) { - if (parse_u32_arg(&argc, &argv, &attr.key_size, + if (parse_u32_arg(&argc, &argv, &key_size, "key size")) - return -1; + goto exit; } else if (is_prefix(*argv, "value")) { - if (parse_u32_arg(&argc, &argv, &attr.value_size, + if (parse_u32_arg(&argc, &argv, &value_size, "value size")) - return -1; + goto exit; } else if (is_prefix(*argv, "entries")) { - if (parse_u32_arg(&argc, &argv, &attr.max_entries, + if (parse_u32_arg(&argc, &argv, &max_entries, "max entries")) - return -1; + goto exit; } else if (is_prefix(*argv, "flags")) { if (parse_u32_arg(&argc, &argv, &attr.map_flags, "flags")) - return -1; + goto exit; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool map create [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to request hardware offload for the map."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); if (attr.map_ifindex) { p_err("offload device already specified"); - return -1; + goto exit; } attr.map_ifindex = if_nametoindex(*argv); if (!attr.map_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); - return -1; + goto exit; } NEXT_ARG(); + } else if (is_prefix(*argv, "inner_map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int inner_map_fd; + + NEXT_ARG(); + if (!REQ_ARGS(2)) + usage(); + inner_map_fd = map_parse_fd_and_info(&argc, &argv, + &info, &len); + if (inner_map_fd < 0) + return -1; + attr.inner_map_fd = inner_map_fd; } else { p_err("unknown arg %s", *argv); - return -1; + goto exit; } } - if (!attr.name) { + if (!map_name) { p_err("map name not specified"); - return -1; + goto exit; } set_max_rlimit(); - fd = bpf_create_map_xattr(&attr); + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); if (fd < 0) { p_err("map create failed: %s", strerror(errno)); - return -1; + goto exit; } err = do_pin_fd(fd, pinfile); close(fd); if (err) - return err; + goto exit; if (json_output) jsonw_null(json_wtr); - return 0; + +exit: + if (attr.inner_map_fd > 0) + close(attr.inner_map_fd); + + return err; } static int do_pop_dequeue(int argc, char **argv) @@ -1565,7 +1436,7 @@ static int do_help(int argc, char **argv) "Usage: %1$s %2$s { show | list } [MAP]\n" " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [dev NAME]\n" + " [inner_map MAP] [offload_dev NAME]\n" " %1$s %2$s dump MAP\n" " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" " %1$s %2$s lookup MAP [key DATA]\n" @@ -1591,8 +1462,10 @@ static int do_help(int argc, char **argv) " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" - " queue | stack | sk_storage | struct_ops | ringbuf }\n" - " " HELP_SPEC_OPTIONS "\n" + " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" + " task_storage | bloom_filter | user_ringbuf | cgrp_storage | arena }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 825f29f93a57..21d7d447e1f3 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -22,7 +22,6 @@ #include <sys/syscall.h> #include <bpf/bpf.h> -#include <perf-sys.h> #include "main.h" @@ -30,13 +29,6 @@ static volatile 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; @@ -125,7 +117,7 @@ int do_event_pipe(int argc, char **argv) .wakeup_events = 1, }; struct bpf_map_info map_info = {}; - struct perf_buffer_raw_opts opts = {}; + LIBBPF_OPTS(perf_buffer_raw_opts, opts); struct event_pipe_ctx ctx = { .all_cpus = true, .cpu = -1, @@ -191,18 +183,14 @@ int do_event_pipe(int argc, char **argv) ctx.idx = 0; } - opts.attr = &perf_attr; - opts.event_cb = print_bpf_output; - opts.ctx = &ctx; opts.cpu_cnt = ctx.all_cpus ? 0 : 1; opts.cpus = &ctx.cpu; opts.map_keys = &ctx.idx; - - pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts); - err = libbpf_get_error(pb); - if (err) { + pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, + print_bpf_output, &ctx, &opts); + if (!pb) { p_err("failed to create perf buffer: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_map; } @@ -217,7 +205,7 @@ int do_event_pipe(int argc, char **argv) err = perf_buffer__poll(pb, 200); if (err < 0 && err != -EINTR) { p_err("perf buffer polling failed: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_pb; } } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 56c3a2bae3ef..968714b4c3d4 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -1,27 +1,33 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (C) 2018 Facebook +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <errno.h> #include <fcntl.h> #include <stdlib.h> #include <string.h> +#include <time.h> #include <unistd.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> #include <net/if.h> -#include <linux/if.h> #include <linux/rtnetlink.h> +#include <linux/socket.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> #include <sys/stat.h> #include <sys/types.h> #include "bpf/nlattr.h" -#include "bpf/libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + struct ip_devname_ifindex { char devname[64]; int ifindex; @@ -70,6 +76,13 @@ static const char * const attach_type_strings[] = { [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", }; +static const char * const attach_loc_strings[] = { + [BPF_TCX_INGRESS] = "tcx/ingress", + [BPF_TCX_EGRESS] = "tcx/egress", + [BPF_NETKIT_PRIMARY] = "netkit/primary", + [BPF_NETKIT_PEER] = "netkit/peer", +}; + const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); static enum net_attach_type parse_attach_type(const char *str) @@ -85,6 +98,266 @@ static enum net_attach_type parse_attach_type(const char *str) return net_attach_type_size; } +typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t, void *cookie); + +static int netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + p_err("Netlink error reporting not supported"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, + __dump_nlmsg_t _fn, dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, (unsigned int)len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +static int netlink_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +static int netlink_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +static int netlink_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +static int netlink_get_link(int sock, unsigned int nl_pid, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -156,8 +429,92 @@ static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) filter_info->devname, filter_info->ifindex); } -static int show_dev_tc_bpf(int sock, unsigned int nl_pid, - struct ip_devname_ifindex *dev) +static int __show_dev_tc_bpf_name(__u32 id, char *name, size_t len) +{ + struct bpf_prog_info info = {}; + __u32 ilen = sizeof(info); + int fd, ret; + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) + return fd; + ret = bpf_obj_get_info_by_fd(fd, &info, &ilen); + if (ret < 0) + goto out; + ret = -ENOENT; + if (info.name[0]) { + get_prog_full_name(&info, fd, name, len); + ret = 0; + } +out: + close(fd); + return ret; +} + +static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev, + const enum bpf_attach_type loc) +{ + __u32 prog_flags[64] = {}, link_flags[64] = {}, i, j; + __u32 prog_ids[64] = {}, link_ids[64] = {}; + LIBBPF_OPTS(bpf_prog_query_opts, optq); + char prog_name[MAX_PROG_FULL_NAME]; + int ret; + + optq.prog_ids = prog_ids; + optq.prog_attach_flags = prog_flags; + optq.link_ids = link_ids; + optq.link_attach_flags = link_flags; + optq.count = ARRAY_SIZE(prog_ids); + + ret = bpf_prog_query_opts(dev->ifindex, loc, &optq); + if (ret) + return; + for (i = 0; i < optq.count; i++) { + NET_START_OBJECT; + NET_DUMP_STR("devname", "%s", dev->devname); + NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex); + NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]); + ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name, + sizeof(prog_name)); + if (!ret) + NET_DUMP_STR("name", " %s", prog_name); + NET_DUMP_UINT("prog_id", " prog_id %u ", prog_ids[i]); + if (prog_flags[i] || json_output) { + NET_START_ARRAY("prog_flags", "%s "); + for (j = 0; prog_flags[i] && j < 32; j++) { + if (!(prog_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + if (link_ids[i] || json_output) { + NET_DUMP_UINT("link_id", "link_id %u ", link_ids[i]); + if (link_flags[i] || json_output) { + NET_START_ARRAY("link_flags", "%s "); + for (j = 0; link_flags[i] && j < 32; j++) { + if (!(link_flags[i] & (1 << j))) + continue; + NET_DUMP_UINT_ONLY(1 << j); + } + NET_END_ARRAY(""); + } + } + NET_END_OBJECT_FINAL; + } +} + +static void show_dev_tc_bpf(struct ip_devname_ifindex *dev) +{ + __show_dev_tc_bpf(dev, BPF_TCX_INGRESS); + __show_dev_tc_bpf(dev, BPF_TCX_EGRESS); + + __show_dev_tc_bpf(dev, BPF_NETKIT_PRIMARY); + __show_dev_tc_bpf(dev, BPF_NETKIT_PEER); +} + +static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid, + struct ip_devname_ifindex *dev) { struct bpf_filter_t filter_info; struct bpf_tcinfo_t tcinfo; @@ -168,14 +525,14 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, tcinfo.array_len = 0; tcinfo.is_qdisc = false; - ret = libbpf_nl_get_class(sock, nl_pid, dev->ifindex, - dump_class_qdisc_nlmsg, &tcinfo); + ret = netlink_get_class(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); if (ret) goto out; tcinfo.is_qdisc = true; - ret = libbpf_nl_get_qdisc(sock, nl_pid, dev->ifindex, - dump_class_qdisc_nlmsg, &tcinfo); + ret = netlink_get_qdisc(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); if (ret) goto out; @@ -183,9 +540,9 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, filter_info.ifindex = dev->ifindex; for (i = 0; i < tcinfo.used_len; i++) { filter_info.kind = tcinfo.handle_array[i].kind; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, - tcinfo.handle_array[i].handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, + tcinfo.handle_array[i].handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; } @@ -193,22 +550,22 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid, /* root, ingress and egress handle */ handle = TC_H_ROOT; filter_info.kind = "root"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); filter_info.kind = "clsact/ingress"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS); filter_info.kind = "clsact/egress"; - ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle, - dump_filter_nlmsg, &filter_info); + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); if (ret) goto out; @@ -287,7 +644,7 @@ static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) flags |= XDP_FLAGS_HW_MODE; - return bpf_set_link_xdp_fd(ifindex, progfd, flags); + return bpf_xdp_attach(ifindex, progfd, flags, NULL); } static int do_attach(int argc, char **argv) @@ -313,8 +670,8 @@ static int do_attach(int argc, char **argv) ifindex = net_parse_dev(&argc, &argv); if (ifindex < 1) { - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } if (argc) { @@ -322,8 +679,8 @@ static int do_attach(int argc, char **argv) overwrite = true; } else { p_err("expected 'overwrite', got: '%s'?", *argv); - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } } @@ -331,17 +688,17 @@ static int do_attach(int argc, char **argv) if (is_prefix("xdp", attach_type_strings[attach_type])) err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); - - if (err < 0) { + if (err) { p_err("interface %s attach failed: %s", attach_type_strings[attach_type], strerror(-err)); - return err; + goto cleanup; } if (json_output) jsonw_null(json_wtr); - - return 0; +cleanup: + close(progfd); + return err; } static int do_detach(int argc, char **argv) @@ -381,12 +738,114 @@ static int do_detach(int argc, char **argv) return 0; } +static int netfilter_link_compar(const void *a, const void *b) +{ + const struct bpf_link_info *nfa = a; + const struct bpf_link_info *nfb = b; + int delta; + + delta = nfa->netfilter.pf - nfb->netfilter.pf; + if (delta) + return delta; + + delta = nfa->netfilter.hooknum - nfb->netfilter.hooknum; + if (delta) + return delta; + + if (nfa->netfilter.priority < nfb->netfilter.priority) + return -1; + if (nfa->netfilter.priority > nfb->netfilter.priority) + return 1; + + return nfa->netfilter.flags - nfb->netfilter.flags; +} + +static void show_link_netfilter(void) +{ + unsigned int nf_link_len = 0, nf_link_count = 0; + struct bpf_link_info *nf_link_info = NULL; + __u32 id = 0; + + while (true) { + struct bpf_link_info info; + int fd, err; + __u32 len; + + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s (id %d)", strerror(errno), id); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get link by id (%u): %s", id, strerror(errno)); + continue; + } + + memset(&info, 0, sizeof(info)); + len = sizeof(info); + + err = bpf_link_get_info_by_fd(fd, &info, &len); + + close(fd); + + if (err) { + p_err("can't get link info for fd %d: %s", fd, strerror(errno)); + continue; + } + + if (info.type != BPF_LINK_TYPE_NETFILTER) + continue; + + if (nf_link_count >= nf_link_len) { + static const unsigned int max_link_count = INT_MAX / sizeof(info); + struct bpf_link_info *expand; + + if (nf_link_count > max_link_count) { + p_err("cannot handle more than %u links\n", max_link_count); + break; + } + + nf_link_len += 16; + + expand = realloc(nf_link_info, nf_link_len * sizeof(info)); + if (!expand) { + p_err("realloc: %s", strerror(errno)); + break; + } + + nf_link_info = expand; + } + + nf_link_info[nf_link_count] = info; + nf_link_count++; + } + + qsort(nf_link_info, nf_link_count, sizeof(*nf_link_info), netfilter_link_compar); + + for (id = 0; id < nf_link_count; id++) { + NET_START_OBJECT; + if (json_output) + netfilter_dump_json(&nf_link_info[id], json_wtr); + else + netfilter_dump_plain(&nf_link_info[id]); + + NET_DUMP_UINT("id", " prog_id %u", nf_link_info[id].prog_id); + NET_END_OBJECT; + } + + free(nf_link_info); +} + static int do_show(int argc, char **argv) { struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; - unsigned int nl_pid; + unsigned int nl_pid = 0; char err_buf[256]; if (argc == 2) { @@ -401,7 +860,7 @@ static int do_show(int argc, char **argv) if (ret) return -1; - sock = libbpf_netlink_open(&nl_pid); + sock = netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); return -1; @@ -416,14 +875,15 @@ static int do_show(int argc, char **argv) jsonw_start_array(json_wtr); NET_START_OBJECT; NET_START_ARRAY("xdp", "%s:\n"); - ret = libbpf_nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); + ret = netlink_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); NET_END_ARRAY("\n"); if (!ret) { NET_START_ARRAY("tc", "%s:\n"); for (i = 0; i < dev_array.used_len; i++) { - ret = show_dev_tc_bpf(sock, nl_pid, - &dev_array.devices[i]); + show_dev_tc_bpf(&dev_array.devices[i]); + ret = show_dev_tc_bpf_classic(sock, nl_pid, + &dev_array.devices[i]); if (ret) break; } @@ -435,6 +895,10 @@ static int do_show(int argc, char **argv) NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); NET_END_ARRAY("\n"); + NET_START_ARRAY("netfilter", "%s:\n"); + show_link_netfilter(); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); @@ -465,8 +929,10 @@ static int do_help(int argc, char **argv) "\n" " " HELP_SPEC_PROGRAM "\n" " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" + " " HELP_SPEC_OPTIONS " }\n" "\n" - "Note: Only xdp and tc attachments are supported now.\n" + "Note: Only xdp, tcx, tc, netkit, flow_dissector and netfilter attachments\n" + " are currently supported.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h index 774af6c62ef5..96318106fb49 100644 --- a/tools/bpf/bpftool/netlink_dumper.h +++ b/tools/bpf/bpftool/netlink_dumper.h @@ -76,6 +76,14 @@ fprintf(stdout, fmt_str, val); \ } +#define NET_DUMP_UINT_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_uint(json_wtr, str); \ + else \ + fprintf(stdout, "%u ", str); \ +} + #define NET_DUMP_STR(name, fmt_str, str) \ { \ if (json_output) \ diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index ad23934819c7..80de2874dabe 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -2,7 +2,9 @@ // Copyright (C) 2018 Facebook // Author: Yonghong Song <yhs@fb.com> +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <ctype.h> #include <errno.h> #include <fcntl.h> @@ -11,7 +13,7 @@ #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> -#include <ftw.h> +#include <dirent.h> #include <bpf/bpf.h> @@ -147,81 +149,83 @@ static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, } } -static int show_proc(const char *fpath, const struct stat *sb, - int tflag, struct FTW *ftwbuf) +static int show_proc(void) { + struct dirent *proc_de, *pid_fd_de; __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; - int err, pid = 0, fd = 0; + DIR *proc, *pid_fd; + int err, pid, fd; const char *pch; char buf[4096]; - /* prefix always /proc */ - pch = fpath + 5; - if (*pch == '\0') - return 0; + proc = opendir("/proc"); + if (!proc) + return -1; - /* 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; + while ((proc_de = readdir(proc))) { + pid = 0; + pch = proc_de->d_name; - /* 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; + /* pid should be all numbers */ + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; - if (json_output) - print_perf_json(pid, fd, prog_id, fd_type, buf, probe_offset, - probe_addr); - else - print_perf_plain(pid, fd, prog_id, fd_type, buf, probe_offset, - probe_addr); + err = snprintf(buf, sizeof(buf), "/proc/%s/fd", proc_de->d_name); + if (err < 0 || err >= (int)sizeof(buf)) + continue; + + pid_fd = opendir(buf); + if (!pid_fd) + continue; + while ((pid_fd_de = readdir(pid_fd))) { + fd = 0; + pch = pid_fd_de->d_name; + + /* fd should be all numbers */ + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, + &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + continue; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + } + closedir(pid_fd); + } + closedir(proc); return 0; } static int do_show(int argc, char **argv) { - int flags = FTW_ACTIONRETVAL | FTW_PHYS; - int err = 0, nopenfd = 16; + int err; 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; - } + err = show_proc(); if (json_output) jsonw_end_array(json_wtr); @@ -231,7 +235,10 @@ static int do_show(int argc, char **argv) static int do_help(int argc, char **argv) { fprintf(stderr, - "Usage: %1$s %2$s { show | list | help }\n" + "Usage: %1$s %2$s { show | list }\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_OPTIONS " }\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c new file mode 100644 index 000000000000..00c77edb6331 --- /dev/null +++ b/tools/bpf/bpftool/pids.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ +#include <errno.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/hashmap.h> + +#include "main.h" +#include "skeleton/pid_iter.h" + +#ifdef BPFTOOL_WITHOUT_SKELETONS + +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) +{ + return -ENOTSUP; +} +void delete_obj_refs_table(struct hashmap *map) {} +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) {} +void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) {} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "pid_iter.skel.h" + +static void add_ref(struct hashmap *map, struct pid_iter_entry *e) +{ + struct hashmap_entry *entry; + struct obj_refs *refs; + struct obj_ref *ref; + int err, i; + void *tmp; + + hashmap__for_each_key_entry(map, entry, e->id) { + refs = entry->pvalue; + + for (i = 0; i < refs->ref_cnt; i++) { + if (refs->refs[i].pid == e->pid) + return; + } + + tmp = realloc(refs->refs, (refs->ref_cnt + 1) * sizeof(*ref)); + if (!tmp) { + p_err("failed to re-alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + refs->refs = tmp; + ref = &refs->refs[refs->ref_cnt]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt++; + + return; + } + + /* new ref */ + refs = calloc(1, sizeof(*refs)); + if (!refs) { + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + + refs->refs = malloc(sizeof(*refs->refs)); + if (!refs->refs) { + free(refs); + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + ref = &refs->refs[0]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt = 1; + refs->has_bpf_cookie = e->has_bpf_cookie; + refs->bpf_cookie = e->bpf_cookie; + + err = hashmap__append(map, e->id, refs); + if (err) + p_err("failed to append entry to hashmap for ID %u: %s", + e->id, strerror(errno)); +} + +static int __printf(2, 0) +libbpf_print_none(__maybe_unused enum libbpf_print_level level, + __maybe_unused const char *format, + __maybe_unused va_list args) +{ + return 0; +} + +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) +{ + struct pid_iter_entry *e; + char buf[4096 / sizeof(*e) * sizeof(*e)]; + struct pid_iter_bpf *skel; + int err, ret, fd = -1, i; + libbpf_print_fn_t default_print; + + *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); + if (IS_ERR(*map)) { + p_err("failed to create hashmap for PID references"); + return -1; + } + set_max_rlimit(); + + skel = pid_iter_bpf__open(); + if (!skel) { + p_err("failed to open PID iterator skeleton"); + return -1; + } + + skel->rodata->obj_type = type; + + /* we don't want output polluted with libbpf errors if bpf_iter is not + * supported + */ + default_print = libbpf_set_print(libbpf_print_none); + err = pid_iter_bpf__load(skel); + libbpf_set_print(default_print); + if (err) { + /* too bad, kernel doesn't support BPF iterators yet */ + err = 0; + goto out; + } + err = pid_iter_bpf__attach(skel); + if (err) { + /* if we loaded above successfully, attach has to succeed */ + p_err("failed to attach PID iterator: %d", err); + goto out; + } + + fd = bpf_iter_create(bpf_link__fd(skel->links.iter)); + if (fd < 0) { + err = -errno; + p_err("failed to create PID iterator session: %d", err); + goto out; + } + + while (true) { + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) { + if (errno == EAGAIN) + continue; + err = -errno; + p_err("failed to read PID iterator output: %d", err); + goto out; + } + if (ret == 0) + break; + if (ret % sizeof(*e)) { + err = -EINVAL; + p_err("invalid PID iterator output format"); + goto out; + } + ret /= sizeof(*e); + + e = (void *)buf; + for (i = 0; i < ret; i++, e++) { + add_ref(*map, e); + } + } + err = 0; +out: + if (fd >= 0) + close(fd); + pid_iter_bpf__destroy(skel); + return err; +} + +void delete_obj_refs_table(struct hashmap *map) +{ + struct hashmap_entry *entry; + size_t bkt; + + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) { + struct obj_refs *refs = entry->pvalue; + + free(refs->refs); + free(refs); + } + + hashmap__free(map); +} + +void emit_obj_refs_json(struct hashmap *map, __u32 id, + json_writer_t *json_writer) +{ + struct hashmap_entry *entry; + + if (hashmap__empty(map)) + return; + + hashmap__for_each_key_entry(map, entry, id) { + struct obj_refs *refs = entry->pvalue; + int i; + + if (refs->ref_cnt == 0) + break; + + if (refs->has_bpf_cookie) + jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie); + + jsonw_name(json_writer, "pids"); + jsonw_start_array(json_writer); + for (i = 0; i < refs->ref_cnt; i++) { + struct obj_ref *ref = &refs->refs[i]; + + jsonw_start_object(json_writer); + jsonw_int_field(json_writer, "pid", ref->pid); + jsonw_string_field(json_writer, "comm", ref->comm); + jsonw_end_object(json_writer); + } + jsonw_end_array(json_writer); + break; + } +} + +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) +{ + struct hashmap_entry *entry; + + if (hashmap__empty(map)) + return; + + hashmap__for_each_key_entry(map, entry, id) { + struct obj_refs *refs = entry->pvalue; + int i; + + if (refs->ref_cnt == 0) + break; + + if (refs->has_bpf_cookie) + printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie); + + printf("%s", prefix); + for (i = 0; i < refs->ref_cnt; i++) { + struct obj_ref *ref = &refs->refs[i]; + + printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid); + } + break; + } +} + + +#endif diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index a5eff83496f2..9cb42a3366c0 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -16,6 +18,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/syscall.h> +#include <dirent.h> #include <linux/err.h> #include <linux/perf_event.h> @@ -23,30 +26,58 @@ #include <bpf/bpf.h> #include <bpf/btf.h> +#include <bpf/hashmap.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> +#include <bpf/skel_internal.h> #include "cfg.h" #include "main.h" #include "xlated_dumper.h" +#define BPF_METADATA_PREFIX "bpf_metadata_" +#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) + enum dump_mode { DUMP_JITED, DUMP_XLATED, }; +static const bool attach_types[] = { + [BPF_SK_SKB_STREAM_PARSER] = true, + [BPF_SK_SKB_STREAM_VERDICT] = true, + [BPF_SK_SKB_VERDICT] = true, + [BPF_SK_MSG_VERDICT] = true, + [BPF_FLOW_DISSECTOR] = true, + [__MAX_BPF_ATTACH_TYPE] = false, +}; + +/* Textual representations traditionally used by the program and kept around + * for the sake of backwards compatibility. + */ static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", + [BPF_SK_SKB_VERDICT] = "skb_verdict", [BPF_SK_MSG_VERDICT] = "msg_verdict", - [BPF_FLOW_DISSECTOR] = "flow_dissector", [__MAX_BPF_ATTACH_TYPE] = NULL, }; +static struct hashmap *prog_table; + static enum bpf_attach_type parse_attach_type(const char *str) { enum bpf_attach_type type; for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_types[type]) { + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!strcmp(str, attach_type_str)) + return type; + } + if (attach_type_strings[type] && is_prefix(str, attach_type_strings[type])) return type; @@ -55,6 +86,76 @@ static enum bpf_attach_type parse_attach_type(const char *str) return __MAX_BPF_ATTACH_TYPE; } +static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode, + void **info_data, size_t *const info_data_sz) +{ + struct bpf_prog_info holder = {}; + size_t needed = 0; + void *ptr; + + if (mode == DUMP_JITED) { + holder.jited_prog_len = info->jited_prog_len; + needed += info->jited_prog_len; + } else { + holder.xlated_prog_len = info->xlated_prog_len; + needed += info->xlated_prog_len; + } + + holder.nr_jited_ksyms = info->nr_jited_ksyms; + needed += info->nr_jited_ksyms * sizeof(__u64); + + holder.nr_jited_func_lens = info->nr_jited_func_lens; + needed += info->nr_jited_func_lens * sizeof(__u32); + + holder.nr_func_info = info->nr_func_info; + holder.func_info_rec_size = info->func_info_rec_size; + needed += info->nr_func_info * info->func_info_rec_size; + + holder.nr_line_info = info->nr_line_info; + holder.line_info_rec_size = info->line_info_rec_size; + needed += info->nr_line_info * info->line_info_rec_size; + + holder.nr_jited_line_info = info->nr_jited_line_info; + holder.jited_line_info_rec_size = info->jited_line_info_rec_size; + needed += info->nr_jited_line_info * info->jited_line_info_rec_size; + + if (needed > *info_data_sz) { + ptr = realloc(*info_data, needed); + if (!ptr) + return -1; + + *info_data = ptr; + *info_data_sz = needed; + } + ptr = *info_data; + + if (mode == DUMP_JITED) { + holder.jited_prog_insns = ptr_to_u64(ptr); + ptr += holder.jited_prog_len; + } else { + holder.xlated_prog_insns = ptr_to_u64(ptr); + ptr += holder.xlated_prog_len; + } + + holder.jited_ksyms = ptr_to_u64(ptr); + ptr += holder.nr_jited_ksyms * sizeof(__u64); + + holder.jited_func_lens = ptr_to_u64(ptr); + ptr += holder.nr_jited_func_lens * sizeof(__u32); + + holder.func_info = ptr_to_u64(ptr); + ptr += holder.nr_func_info * holder.func_info_rec_size; + + holder.line_info = ptr_to_u64(ptr); + ptr += holder.nr_line_info * holder.line_info_rec_size; + + holder.jited_line_info = ptr_to_u64(ptr); + ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size; + + *info = holder; + return 0; +} + static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) { struct timespec real_time_ts, boot_time_ts; @@ -86,198 +187,246 @@ 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_nametag(void *nametag, int **fds, bool tag) +static void show_prog_maps(int fd, __u32 num_maps) { - unsigned int id = 0; - int fd, nb_fds = 0; - void *tmp; + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + __u32 map_ids[num_maps]; + unsigned int i; int err; - while (true) { - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); + info.nr_map_ids = num_maps; + info.map_ids = ptr_to_u64(map_ids); - err = bpf_prog_get_next_id(id, &id); - if (err) { - if (errno != ENOENT) { - p_err("%s", strerror(errno)); - goto err_close_fds; - } - return nb_fds; - } + err = bpf_prog_get_info_by_fd(fd, &info, &len); + if (err || !info.nr_map_ids) + return; - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) { - p_err("can't get prog by id (%u): %s", - id, strerror(errno)); - goto err_close_fds; - } + if (json_output) { + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); + for (i = 0; i < info.nr_map_ids; i++) + jsonw_uint(json_wtr, map_ids[i]); + jsonw_end_array(json_wtr); + } else { + printf(" map_ids "); + for (i = 0; i < info.nr_map_ids; i++) + printf("%u%s", map_ids[i], + i == info.nr_map_ids - 1 ? "" : ","); + } +} - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err) { - p_err("can't get prog info (%u): %s", - id, strerror(errno)); - goto err_close_fd; +static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) +{ + struct bpf_prog_info prog_info; + __u32 prog_info_len; + __u32 map_info_len; + void *value = NULL; + __u32 *map_ids; + int nr_maps; + int key = 0; + int map_fd; + int ret; + __u32 i; + + memset(&prog_info, 0, sizeof(prog_info)); + prog_info_len = sizeof(prog_info); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + if (ret) + return NULL; + + if (!prog_info.nr_map_ids) + return NULL; + + map_ids = calloc(prog_info.nr_map_ids, sizeof(__u32)); + if (!map_ids) + return NULL; + + nr_maps = prog_info.nr_map_ids; + memset(&prog_info, 0, sizeof(prog_info)); + prog_info.nr_map_ids = nr_maps; + prog_info.map_ids = ptr_to_u64(map_ids); + prog_info_len = sizeof(prog_info); + + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + if (ret) + goto free_map_ids; + + for (i = 0; i < prog_info.nr_map_ids; i++) { + map_fd = bpf_map_get_fd_by_id(map_ids[i]); + if (map_fd < 0) + goto free_map_ids; + + memset(map_info, 0, sizeof(*map_info)); + map_info_len = sizeof(*map_info); + ret = bpf_map_get_info_by_fd(map_fd, map_info, &map_info_len); + if (ret < 0) { + close(map_fd); + goto free_map_ids; } - if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || - (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { - close(fd); + if (map_info->type != BPF_MAP_TYPE_ARRAY || + map_info->key_size != sizeof(int) || + map_info->max_entries != 1 || + !map_info->btf_value_type_id || + !strstr(map_info->name, ".rodata")) { + close(map_fd); continue; } - 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; + value = malloc(map_info->value_size); + if (!value) { + close(map_fd); + goto free_map_ids; } - (*fds)[nb_fds++] = fd; + + if (bpf_map_lookup_elem(map_fd, &key, value)) { + close(map_fd); + free(value); + value = NULL; + goto free_map_ids; + } + + close(map_fd); + break; } -err_close_fd: - close(fd); -err_close_fds: - while (--nb_fds >= 0) - close((*fds)[nb_fds]); - return -1; +free_map_ids: + free(map_ids); + return value; } -static int prog_parse_fds(int *argc, char ***argv, int **fds) +static bool has_metadata_prefix(const char *s) { - if (is_prefix(**argv, "id")) { - unsigned int id; - char *endptr; - - NEXT_ARGP(); + return strncmp(s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) == 0; +} - id = strtoul(**argv, &endptr, 0); - if (*endptr) { - p_err("can't parse %s as ID", **argv); - return -1; - } - NEXT_ARGP(); +static void show_prog_metadata(int fd, __u32 num_maps) +{ + const struct btf_type *t_datasec, *t_var; + struct bpf_map_info map_info; + struct btf_var_secinfo *vsi; + bool printed_header = false; + unsigned int i, vlen; + void *value = NULL; + const char *name; + struct btf *btf; + int err; - (*fds)[0] = bpf_prog_get_fd_by_id(id); - if ((*fds)[0] < 0) { - p_err("get by id (%u): %s", id, strerror(errno)); - return -1; - } - return 1; - } else if (is_prefix(**argv, "tag")) { - unsigned char tag[BPF_TAG_SIZE]; + if (!num_maps) + return; - NEXT_ARGP(); + memset(&map_info, 0, sizeof(map_info)); + value = find_metadata(fd, &map_info); + if (!value) + return; - if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, - tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) - != BPF_TAG_SIZE) { - p_err("can't parse tag"); - return -1; - } - NEXT_ARGP(); + btf = btf__load_from_kernel_by_id(map_info.btf_id); + if (!btf) + goto out_free; - return prog_fd_by_nametag(tag, fds, true); - } else if (is_prefix(**argv, "name")) { - char *name; + t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id); + if (!btf_is_datasec(t_datasec)) + goto out_free; - NEXT_ARGP(); + vlen = btf_vlen(t_datasec); + vsi = btf_var_secinfos(t_datasec); - name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { - p_err("can't parse name"); - return -1; - } - NEXT_ARGP(); + /* We don't proceed to check the kinds of the elements of the DATASEC. + * The verifier enforces them to be BTF_KIND_VAR. + */ - return prog_fd_by_nametag(name, fds, false); - } else if (is_prefix(**argv, "pinned")) { - char *path; + if (json_output) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; - NEXT_ARGP(); + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); - path = **argv; - NEXT_ARGP(); + if (!has_metadata_prefix(name)) + continue; - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); - if ((*fds)[0] < 0) - return -1; - return 1; - } + if (!printed_header) { + jsonw_name(json_wtr, "metadata"); + jsonw_start_object(json_wtr); + printed_header = true; + } - p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); - return -1; -} + jsonw_name(json_wtr, name + BPF_METADATA_PREFIX_LEN); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_end_object(json_wtr); + } else { + json_writer_t *btf_wtr; + struct btf_dumper d = { + .btf = btf, + .is_plain_text = true, + }; -int prog_parse_fd(int *argc, char ***argv) -{ - int *fds = NULL; - int nb_fds, fd; + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); - 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; - } + if (!has_metadata_prefix(name)) + continue; - fd = fds[0]; -exit_free: - free(fds); - return fd; -} + if (!printed_header) { + printf("\tmetadata:"); -static void show_prog_maps(int fd, __u32 num_maps) -{ - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); - __u32 map_ids[num_maps]; - unsigned int i; - int err; + btf_wtr = jsonw_new(stdout); + if (!btf_wtr) { + p_err("jsonw alloc failed"); + goto out_free; + } + d.jw = btf_wtr, - info.nr_map_ids = num_maps; - info.map_ids = ptr_to_u64(map_ids); + printed_header = true; + } - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err || !info.nr_map_ids) - return; + printf("\n\t\t%s = ", name + BPF_METADATA_PREFIX_LEN); - if (json_output) { - jsonw_name(json_wtr, "map_ids"); - jsonw_start_array(json_wtr); - for (i = 0; i < info.nr_map_ids; i++) - jsonw_uint(json_wtr, map_ids[i]); - jsonw_end_array(json_wtr); - } else { - printf(" map_ids "); - for (i = 0; i < info.nr_map_ids; i++) - printf("%u%s", map_ids[i], - i == info.nr_map_ids - 1 ? "" : ","); + jsonw_reset(btf_wtr); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_destroy(&btf_wtr); } + +out_free: + btf__free(btf); + free(value); } -static void print_prog_header_json(struct bpf_prog_info *info) +static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - jsonw_string_field(json_wtr, "type", - prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + + if (prog_type_str) + jsonw_string_field(json_wtr, "type", prog_type_str); else jsonw_uint_field(json_wtr, "type", info->type); - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } jsonw_name(json_wtr, "tag"); jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", @@ -289,14 +438,16 @@ static void print_prog_header_json(struct bpf_prog_info *info) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } + if (info->recursion_misses) + jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses); } -static void print_prog_json(struct bpf_prog_info *info, int fd) +static void print_prog_json(struct bpf_prog_info *info, int fd, bool orphaned) { char *memlock; jsonw_start_object(json_wtr); - print_prog_header_json(info); + print_prog_header_json(info, fd); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -310,6 +461,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_uint_field(json_wtr, "uid", info->created_by_uid); } + jsonw_bool_field(json_wtr, "orphaned", orphaned); jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len); if (info->jited_prog_len) { @@ -321,7 +473,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) memlock = get_fdinfo(fd, "memlock"); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->nr_map_ids) @@ -330,31 +482,39 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) if (info->btf_id) jsonw_int_field(json_wtr, "btf_id", info->btf_id); - if (!hash_empty(prog_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; jsonw_name(json_wtr, "pinned"); jsonw_start_array(json_wtr); - hash_for_each_possible(prog_table.table, obj, hash, info->id) { - if (obj->id == info->id) - jsonw_string(json_wtr, obj->path); - } + hashmap__for_each_key_entry(prog_table, entry, info->id) + jsonw_string(json_wtr, entry->pvalue); jsonw_end_array(json_wtr); } + emit_obj_refs_json(refs_table, info->id, json_wtr); + + show_prog_metadata(fd, info->nr_map_ids); + jsonw_end_object(json_wtr); } -static void print_prog_header_plain(struct bpf_prog_info *info) +static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - printf("%s ", prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + if (prog_type_str) + printf("%s ", prog_type_str); else printf("type %u ", info->type); - if (*info->name) - printf("name %s ", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); @@ -363,14 +523,16 @@ static void print_prog_header_plain(struct bpf_prog_info *info) if (info->run_time_ns) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); + if (info->recursion_misses) + printf(" recursion_misses %lld", info->recursion_misses); printf("\n"); } -static void print_prog_plain(struct bpf_prog_info *info, int fd) +static void print_prog_plain(struct bpf_prog_info *info, int fd, bool orphaned) { char *memlock; - print_prog_header_plain(info); + print_prog_header_plain(info, fd); if (info->load_time) { char buf[32]; @@ -393,22 +555,27 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf(" memlock %sB", memlock); free(memlock); + if (orphaned) + printf(" orphaned"); + if (info->nr_map_ids) show_prog_maps(fd, info->nr_map_ids); - if (!hash_empty(prog_table.table)) { - struct pinned_obj *obj; + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; - hash_for_each_possible(prog_table.table, obj, hash, info->id) { - if (obj->id == info->id) - printf("\n\tpinned %s", obj->path); - } + hashmap__for_each_key_entry(prog_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); } if (info->btf_id) printf("\n\tbtf_id %d", info->btf_id); + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + printf("\n"); + + show_prog_metadata(fd, info->nr_map_ids); } static int show_prog(int fd) @@ -417,16 +584,16 @@ static int show_prog(int fd) __u32 len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(fd, &info, &len); - if (err) { + err = bpf_prog_get_info_by_fd(fd, &info, &len); + if (err && err != -ENODEV) { p_err("can't get prog info: %s", strerror(errno)); return -1; } if (json_output) - print_prog_json(&info, fd); + print_prog_json(&info, fd, err == -ENODEV); else - print_prog_plain(&info, fd); + print_prog_plain(&info, fd, err == -ENODEV); return 0; } @@ -471,8 +638,16 @@ static int do_show(int argc, char **argv) int err; int fd; - if (show_pinned) - build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); + if (show_pinned) { + prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(prog_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(prog_table, BPF_OBJ_PROG); + } + build_obj_refs_table(&refs_table, BPF_OBJ_PROG); if (argc == 2) return do_show_subset(argc, argv); @@ -514,6 +689,11 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(prog_table); + return err; } @@ -529,31 +709,34 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, char func_sig[1024]; unsigned char *buf; __u32 member_len; + int fd, err = -1; ssize_t n; - int fd; if (mode == DUMP_JITED) { if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); return -1; } - buf = (unsigned char *)(info->jited_prog_insns); + buf = u64_to_ptr(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } - buf = (unsigned char *)info->xlated_prog_insns; + buf = u64_to_ptr(info->xlated_prog_insns); member_len = info->xlated_prog_len; } - if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { - p_err("failed to get btf"); - return -1; + if (info->btf_id) { + btf = btf__load_from_kernel_by_id(info->btf_id); + if (!btf) { + p_err("failed to get btf"); + return -1; + } } - func_info = (void *)info->func_info; + func_info = u64_to_ptr(info->func_info); if (info->nr_line_info) { prog_linfo = bpf_prog_linfo__new(info); @@ -566,15 +749,15 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, if (fd < 0) { p_err("can't open file %s: %s", filepath, strerror(errno)); - return -1; + goto exit_free; } n = write(fd, buf, member_len); close(fd); - if (n != member_len) { + if (n != (ssize_t)member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); - return -1; + goto exit_free; } if (json_output) @@ -583,12 +766,10 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, const char *name = NULL; if (info->ifindex) { - name = ifindex_to_bfd_params(info->ifindex, - info->netns_dev, - info->netns_ino, - &disasm_opt); + name = ifindex_to_arch(info->ifindex, info->netns_dev, + info->netns_ino, &disasm_opt); if (!name) - return -1; + goto exit_free; } if (info->nr_jited_func_lens && info->jited_func_lens) { @@ -601,13 +782,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, __u32 i; if (info->nr_jited_ksyms) { kernel_syms_load(&dd); - ksyms = (__u64 *) info->jited_ksyms; + ksyms = u64_to_ptr(info->jited_ksyms); } if (json_output) jsonw_start_array(json_wtr); - lens = (__u32 *) info->jited_func_lens; + lens = u64_to_ptr(info->jited_func_lens); for (i = 0; i < info->nr_jited_func_lens; i++) { if (ksyms) { sym = kernel_syms_search(&dd, ksyms[i]); @@ -641,10 +822,11 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, printf("%s:\n", sym_name); } - disasm_print_insn(img, lens[i], opcodes, - name, disasm_opt, btf, - prog_linfo, ksyms[i], i, - linum); + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + prog_linfo, ksyms[i], i, + linum)) + goto exit_free; img += lens[i]; @@ -657,47 +839,51 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, if (json_output) jsonw_end_array(json_wtr); } else { - disasm_print_insn(buf, member_len, opcodes, name, - disasm_opt, btf, NULL, 0, 0, false); + if (disasm_print_insn(buf, member_len, opcodes, name, + disasm_opt, btf, NULL, 0, 0, + false)) + goto exit_free; } - } else if (visual) { - if (json_output) - jsonw_null(json_wtr); - else - dump_xlated_cfg(buf, member_len); } else { kernel_syms_load(&dd); dd.nr_jited_ksyms = info->nr_jited_ksyms; - dd.jited_ksyms = (__u64 *) info->jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); dd.btf = btf; dd.func_info = func_info; dd.finfo_rec_size = info->func_info_rec_size; dd.prog_linfo = prog_linfo; if (json_output) - dump_xlated_json(&dd, buf, member_len, opcodes, - linum); + dump_xlated_json(&dd, buf, member_len, opcodes, linum); + else if (visual) + dump_xlated_cfg(&dd, buf, member_len, opcodes, linum); else - dump_xlated_plain(&dd, buf, member_len, opcodes, - linum); + dump_xlated_plain(&dd, buf, member_len, opcodes, linum); kernel_syms_destroy(&dd); } - return 0; + err = 0; + +exit_free: + btf__free(btf); + bpf_prog_linfo__free(prog_linfo); + return err; } static int do_dump(int argc, char **argv) { - struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + size_t info_data_sz = 0; + void *info_data = NULL; char *filepath = NULL; bool opcodes = false; bool visual = false; enum dump_mode mode; bool linum = false; - int *fds = NULL; int nb_fds, i = 0; + int *fds = NULL; int err = -1; - __u64 arrays; if (is_prefix(*argv, "jited")) { if (disasm_init()) @@ -723,77 +909,87 @@ static int do_dump(int argc, char **argv) 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; - } + while (argc) { + 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"); + 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(); + } else { + usage(); goto exit_close; } - - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); } - if (argc) { - usage(); + if (filepath && (opcodes || visual || linum)) { + p_err("'file' is not compatible with 'opcodes', 'visual', or 'linum'"); + goto exit_close; + } + if (json_output && visual) { + p_err("'visual' is not compatible with JSON output"); 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)) { + memset(&info, 0, sizeof(info)); + + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + err = prep_prog_info(&info, mode, &info_data, &info_data_sz); + if (err) { + p_err("can't grow prog info_data"); + break; + } + + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); + if (err) { p_err("can't get prog info: %s", strerror(errno)); break; } if (json_output && nb_fds > 1) { jsonw_start_object(json_wtr); /* prog object */ - print_prog_header_json(&info_linear->info); + print_prog_header_json(&info, fds[i]); jsonw_name(json_wtr, "insns"); } else if (nb_fds > 1) { - print_prog_header_plain(&info_linear->info); + print_prog_header_plain(&info, fds[i]); } - err = prog_dump(&info_linear->info, mode, filepath, opcodes, - visual, linum); + err = prog_dump(&info, mode, filepath, opcodes, visual, linum); if (json_output && nb_fds > 1) jsonw_end_object(json_wtr); /* prog object */ else if (i != nb_fds - 1 && nb_fds > 1) printf("\n"); - free(info_linear); if (err) break; close(fds[i]); @@ -805,6 +1001,7 @@ exit_close: for (; i < nb_fds; i++) close(fds[i]); exit_free: + free(info_data); free(fds); return err; } @@ -850,7 +1047,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } @@ -1072,12 +1269,12 @@ static int do_run(int argc, char **argv) { char *data_fname_in = NULL, *data_fname_out = NULL; char *ctx_fname_in = NULL, *ctx_fname_out = NULL; - struct bpf_prog_test_run_attr test_attr = {0}; const unsigned int default_size = SZ_32K; void *data_in = NULL, *data_out = NULL; void *ctx_in = NULL, *ctx_out = NULL; unsigned int repeat = 1; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); if (!REQ_ARGS(4)) return -1; @@ -1195,14 +1392,13 @@ static int do_run(int argc, char **argv) goto free_ctx_in; } - test_attr.prog_fd = fd; test_attr.repeat = repeat; test_attr.data_in = data_in; test_attr.data_out = data_out; test_attr.ctx_in = ctx_in; test_attr.ctx_out = ctx_out; - err = bpf_prog_test_run_xattr(&test_attr); + err = bpf_prog_test_run_opts(fd, &test_attr); if (err) { p_err("failed to run program: %s", strerror(errno)); goto free_ctx_out; @@ -1266,23 +1462,72 @@ get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, return ret; } +static int +auto_attach_program(struct bpf_program *prog, const char *path) +{ + struct bpf_link *link; + int err; + + link = bpf_program__attach(prog); + if (!link) { + p_info("Program %s does not support autoattach, falling back to pinning", + bpf_program__name(prog)); + return bpf_obj_pin(bpf_program__fd(prog), path); + } + + err = bpf_link__pin(link, path); + bpf_link__destroy(link); + return err; +} + +static int +auto_attach_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + char buf[PATH_MAX]; + int err; + + bpf_object__for_each_program(prog, obj) { + err = pathname_concat(buf, sizeof(buf), path, bpf_program__name(prog)); + if (err) + goto err_unpin_programs; + + err = auto_attach_program(prog, buf); + if (err) + goto err_unpin_programs; + } + + return 0; + +err_unpin_programs: + while ((prog = bpf_object__prev_program(obj, prog))) { + if (pathname_concat(buf, sizeof(buf), path, bpf_program__name(prog))) + continue; + + bpf_program__unpin(prog, buf); + } + + return err; +} + static int load_with_options(int argc, char **argv, bool first_prog_only) { enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, .relaxed_maps = relaxed_maps, ); - struct bpf_object_load_attr load_attr = { 0 }; enum bpf_attach_type expected_attach_type; struct map_replace *map_replace = NULL; struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; const char *pinmaps = NULL; + __u32 xdpmeta_ifindex = 0; + __u32 offload_ifindex = 0; + bool auto_attach = false; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; unsigned int i, j; - __u32 ifindex = 0; const char *file; int idx, err; @@ -1294,8 +1539,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) while (argc) { if (is_prefix(*argv, "type")) { - char *type; - NEXT_ARG(); if (common_prog_type != BPF_PROG_TYPE_UNSPEC) { @@ -1305,21 +1548,26 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) 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(*argv, &common_prog_type, + &expected_attach_type); + if (err < 0) { + /* Put a '/' at the end of type to appease libbpf */ + char *type = malloc(strlen(*argv) + 2); - err = get_prog_type_by_name(type, &common_prog_type, - &expected_attach_type); - free(type); - if (err < 0) - goto err_free_reuse_maps; + if (!type) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + *type = 0; + strcat(type, *argv); + strcat(type, "/"); + + err = get_prog_type_by_name(type, &common_prog_type, + &expected_attach_type); + free(type); + if (err < 0) + goto err_free_reuse_maps; + } NEXT_ARG(); } else if (is_prefix(*argv, "map")) { @@ -1357,9 +1605,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) if (fd < 0) goto err_free_reuse_maps; - new_map_replace = reallocarray(map_replace, - old_map_fds + 1, - sizeof(*map_replace)); + new_map_replace = libbpf_reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); if (!new_map_replace) { p_err("mem alloc failed"); goto err_free_reuse_maps; @@ -1371,17 +1619,46 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) map_replace[old_map_fds].fd = fd; old_map_fds++; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool prog load [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to offload program to device.\n" + "For applications using XDP hints only, use 'xdpmeta_dev <ifname>'."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: + NEXT_ARG(); + + if (offload_ifindex) { + p_err("offload_dev already specified"); + goto err_free_reuse_maps; + } else if (xdpmeta_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + offload_ifindex = if_nametoindex(*argv); + if (!offload_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "xdpmeta_dev")) { NEXT_ARG(); - if (ifindex) { - p_err("offload device already specified"); + if (xdpmeta_ifindex) { + p_err("xdpmeta_dev already specified"); + goto err_free_reuse_maps; + } else if (offload_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); goto err_free_reuse_maps; } if (!REQ_ARGS(1)) goto err_free_reuse_maps; - ifindex = if_nametoindex(*argv); - if (!ifindex) { + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); goto err_free_reuse_maps; @@ -1394,6 +1671,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_free_reuse_maps; pinmaps = GET_ARG(); + } else if (is_prefix(*argv, "autoattach")) { + auto_attach = true; + NEXT_ARG(); } else { p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?", *argv); @@ -1403,8 +1683,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) set_max_rlimit(); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_file(file, &open_opts); - if (IS_ERR_OR_NULL(obj)) { + if (!obj) { p_err("failed to open object file"); goto err_free_reuse_maps; } @@ -1413,7 +1697,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) enum bpf_prog_type prog_type = common_prog_type; if (prog_type == BPF_PROG_TYPE_UNSPEC) { - const char *sec_name = bpf_program__title(pos, false); + const char *sec_name = bpf_program__section_name(pos); err = get_prog_type_by_name(sec_name, &prog_type, &expected_attach_type); @@ -1421,8 +1705,14 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - bpf_program__set_ifindex(pos, ifindex); - bpf_program__set_type(pos, prog_type); + if (prog_type == BPF_PROG_TYPE_XDP && xdpmeta_ifindex) { + bpf_program__set_flags(pos, BPF_F_XDP_DEV_BOUND_ONLY); + bpf_program__set_ifindex(pos, xdpmeta_ifindex); + } else { + bpf_program__set_ifindex(pos, offload_ifindex); + } + if (bpf_program__type(pos) != prog_type) + bpf_program__set_type(pos, prog_type); bpf_program__set_expected_attach_type(pos, expected_attach_type); } @@ -1457,8 +1747,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) j = 0; idx = 0; bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) - bpf_map__set_ifindex(map, ifindex); + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + bpf_map__set_ifindex(map, offload_ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { err = bpf_map__reuse_fd(map, map_replace[j++].fd); @@ -1482,36 +1772,37 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile); + err = mount_bpffs_for_pin(pinfile, !first_prog_only); if (err) goto err_close_obj; if (first_prog_only) { - prog = bpf_program__next(NULL, obj); + prog = bpf_object__next_program(obj, NULL); if (!prog) { p_err("object file doesn't contain any bpf program"); goto err_close_obj; } - err = bpf_obj_pin(bpf_program__fd(prog), pinfile); + if (auto_attach) + err = auto_attach_program(prog, pinfile); + else + err = bpf_obj_pin(bpf_program__fd(prog), pinfile); if (err) { p_err("failed to pin program %s", - bpf_program__title(prog, false)); + bpf_program__section_name(prog)); goto err_close_obj; } } else { - err = bpf_object__pin_programs(obj, pinfile); + if (auto_attach) + err = auto_attach_programs(obj, pinfile); + else + err = bpf_object__pin_programs(obj, pinfile); if (err) { p_err("failed to pin all programs"); goto err_close_obj; @@ -1550,8 +1841,110 @@ err_free_reuse_maps: return -1; } +static int count_open_fds(void) +{ + DIR *dp = opendir("/proc/self/fd"); + struct dirent *de; + int cnt = -3; + + if (!dp) + return -1; + + while ((de = readdir(dp))) + cnt++; + + closedir(dp); + return cnt; +} + +static int try_loader(struct gen_loader_opts *gen) +{ + struct bpf_load_and_run_opts opts = {}; + struct bpf_loader_ctx *ctx; + int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc), + sizeof(struct bpf_prog_desc)); + int log_buf_sz = (1u << 24) - 1; + int err, fds_before, fd_delta; + char *log_buf = NULL; + + ctx = alloca(ctx_sz); + memset(ctx, 0, ctx_sz); + ctx->sz = ctx_sz; + if (verifier_logs) { + ctx->log_level = 1 + 2 + 4; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + } + opts.ctx = ctx; + opts.data = gen->data; + opts.data_sz = gen->data_sz; + opts.insns = gen->insns; + opts.insns_sz = gen->insns_sz; + fds_before = count_open_fds(); + err = bpf_load_and_run(&opts); + fd_delta = count_open_fds() - fds_before; + if (err < 0 || verifier_logs) { + fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); + if (fd_delta && err < 0) + fprintf(stderr, "loader prog leaked %d FDs\n", + fd_delta); + } + free(log_buf); + return err; +} + +static int do_loader(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); + DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); + struct bpf_object *obj; + const char *file; + int err = 0; + + if (!REQ_ARGS(1)) + return -1; + file = GET_ARG(); + + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (!obj) { + p_err("failed to open object file"); + goto err_close_obj; + } + + err = bpf_object__gen_loader(obj, &gen); + if (err) + goto err_close_obj; + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (verifier_logs) { + struct dump_data dd = {}; + + kernel_syms_load(&dd); + dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false); + kernel_syms_destroy(&dd); + } + err = try_loader(&gen); +err_close_obj: + bpf_object__close(obj); + return err; +} + static int do_load(int argc, char **argv) { + if (use_loader) + return do_loader(argc, argv); return load_with_options(argc, argv, true); } @@ -1627,6 +2020,34 @@ struct profile_metric { .ratio_desc = "LLC misses per million insns", .ratio_mul = 1e6, }, + { + .name = "itlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "itlb misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "dtlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "dtlb misses per million insns", + .ratio_mul = 1e6, + }, }; static __u64 profile_total_count; @@ -1639,7 +2060,7 @@ static int profile_parse_metrics(int argc, char **argv) int selected_cnt = 0; unsigned int i; - metric_cnt = sizeof(metrics) / sizeof(struct profile_metric); + metric_cnt = ARRAY_SIZE(metrics); while (argc > 0) { for (i = 0; i < metric_cnt; i++) { @@ -1771,35 +2192,58 @@ static void profile_print_readings(void) static char *profile_target_name(int tgt_fd) { - struct bpf_prog_info_linear *info_linear; - struct bpf_func_info *func_info; + struct bpf_func_info func_info; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); const struct btf_type *t; + __u32 func_info_rec_size; + struct btf *btf = NULL; char *name = NULL; - struct btf *btf; + int err; - info_linear = bpf_program__get_prog_info_linear( - tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("failed to get info_linear for prog FD %d", tgt_fd); - return NULL; + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to get info for prog FD %d", tgt_fd); + goto out; } - if (info_linear->info.btf_id == 0 || - btf__get_from_id(info_linear->info.btf_id, &btf)) { + if (info.btf_id == 0) { p_err("prog FD %d doesn't have valid btf", tgt_fd); goto out; } - func_info = (struct bpf_func_info *)(info_linear->info.func_info); - t = btf__type_by_id(btf, func_info[0].type_id); + func_info_rec_size = info.func_info_rec_size; + if (info.nr_func_info == 0) { + p_err("found 0 func_info for prog FD %d", tgt_fd); + goto out; + } + + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = func_info_rec_size; + info.func_info = ptr_to_u64(&func_info); + + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to get func_info for prog FD %d", tgt_fd); + goto out; + } + + btf = btf__load_from_kernel_by_id(info.btf_id); + if (!btf) { + p_err("failed to load btf for prog FD %d", tgt_fd); + goto out; + } + + t = btf__type_by_id(btf, func_info.type_id); if (!t) { p_err("btf %d doesn't have type %d", - info_linear->info.btf_id, func_info[0].type_id); + info.btf_id, func_info.type_id); goto out; } name = strdup(btf__name_by_offset(btf, t->name_off)); out: - free(info_linear); + btf__free(btf); return name; } @@ -1820,13 +2264,41 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( - sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int)); if (!profile_perf_events) { p_err("failed to allocate memory for perf_event array: %s", strerror(errno)); @@ -1842,17 +2314,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; @@ -1924,10 +2390,10 @@ static int do_profile(int argc, char **argv) profile_obj->rodata->num_metric = num_metric; /* adjust map sizes */ - bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu); - bpf_map__resize(profile_obj->maps.fentry_readings, num_metric); - bpf_map__resize(profile_obj->maps.accum_readings, num_metric); - bpf_map__resize(profile_obj->maps.counts, 1); + bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.counts, 1); /* change target name */ profile_tgt_name = profile_target_name(profile_tgt_fd); @@ -1985,13 +2451,14 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [PROG]\n" - " %1$s %2$s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n" - " %1$s %2$s dump jited PROG [{ file FILE | opcodes | linum }]\n" + " %1$s %2$s dump xlated PROG [{ file FILE | [opcodes] [linum] [visual] }]\n" + " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" " %1$s %2$s pin PROG FILE\n" " %1$s %2$s { load | loadall } OBJ PATH \\\n" - " [type TYPE] [dev NAME] \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" + " [autoattach]\n" " %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n" " %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n" " %1$s %2$s run PROG \\\n" @@ -2012,15 +2479,18 @@ static int do_help(int argc, char **argv) " sk_reuseport | flow_dissector | cgroup/sysctl |\n" " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" - " cgroup/getpeername4 | cgroup/getpeername6 |\n" - " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" - " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" - " cgroup/getsockopt | cgroup/setsockopt |\n" - " struct_ops | fentry | fexit | freplace }\n" - " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" - " flow_dissector }\n" - " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n" - " " HELP_SPEC_OPTIONS "\n" + " cgroup/connect_unix | cgroup/getpeername4 | cgroup/getpeername6 |\n" + " cgroup/getpeername_unix | cgroup/getsockname4 | cgroup/getsockname6 |\n" + " cgroup/getsockname_unix | cgroup/sendmsg4 | cgroup/sendmsg6 |\n" + " cgroup/sendmsg°unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" + " struct_ops | fentry | fexit | freplace | sk_lookup }\n" + " ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n" + " sk_skb_stream_parser | flow_dissector }\n" + " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n" + " {-L|--use-loader} }\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c new file mode 100644 index 000000000000..26004f0c5a6a --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2020 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_tracing.h> +#include "pid_iter.h" + +/* keep in sync with the definition in main.h */ +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, + BPF_OBJ_LINK, + BPF_OBJ_BTF, +}; + +struct bpf_perf_link___local { + struct bpf_link link; + struct file *perf_file; +} __attribute__((preserve_access_index)); + +struct perf_event___local { + u64 bpf_cookie; +} __attribute__((preserve_access_index)); + +enum bpf_link_type___local { + BPF_LINK_TYPE_PERF_EVENT___local = 7, +}; + +extern const void bpf_link_fops __ksym; +extern const void bpf_map_fops __ksym; +extern const void bpf_prog_fops __ksym; +extern const void btf_fops __ksym; + +const volatile enum bpf_obj_type obj_type = BPF_OBJ_UNKNOWN; + +static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) +{ + switch (type) { + case BPF_OBJ_PROG: + return BPF_CORE_READ((struct bpf_prog *)ent, aux, id); + case BPF_OBJ_MAP: + return BPF_CORE_READ((struct bpf_map *)ent, id); + case BPF_OBJ_BTF: + return BPF_CORE_READ((struct btf *)ent, id); + case BPF_OBJ_LINK: + return BPF_CORE_READ((struct bpf_link *)ent, id); + default: + return 0; + } +} + +/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ +static __u64 get_bpf_cookie(struct bpf_link *link) +{ + struct bpf_perf_link___local *perf_link; + struct perf_event___local *event; + + perf_link = container_of(link, struct bpf_perf_link___local, link); + event = BPF_CORE_READ(perf_link, perf_file, private_data); + return BPF_CORE_READ(event, bpf_cookie); +} + +SEC("iter/task_file") +int iter(struct bpf_iter__task_file *ctx) +{ + struct file *file = ctx->file; + struct task_struct *task = ctx->task; + struct pid_iter_entry e; + const void *fops; + + if (!file || !task) + return 0; + + switch (obj_type) { + case BPF_OBJ_PROG: + fops = &bpf_prog_fops; + break; + case BPF_OBJ_MAP: + fops = &bpf_map_fops; + break; + case BPF_OBJ_BTF: + fops = &btf_fops; + break; + case BPF_OBJ_LINK: + fops = &bpf_link_fops; + break; + default: + return 0; + } + + if (file->f_op != fops) + return 0; + + __builtin_memset(&e, 0, sizeof(e)); + e.pid = task->tgid; + e.id = get_obj_id(file->private_data, obj_type); + + if (obj_type == BPF_OBJ_LINK && + bpf_core_enum_value_exists(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + struct bpf_link *link = (struct bpf_link *) file->private_data; + + if (link->type == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), + task->group_leader->comm); + bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h new file mode 100644 index 000000000000..bbb570d4cca6 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (c) 2020 Facebook */ +#ifndef __PID_ITER_H +#define __PID_ITER_H + +struct pid_iter_entry { + __u32 id; + int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; + char comm[16]; +}; + +#endif diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 20034c12f7c5..2f80edc682f1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -1,10 +1,15 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include "profiler.h" -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + /* map of perf event fds, num_cpu * num_metric entries */ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -16,14 +21,14 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } fentry_readings SEC(".maps"); /* accumulated readings */ struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } accum_readings SEC(".maps"); /* sample counts, one per cpu */ @@ -40,7 +45,7 @@ const volatile __u32 num_metric = 1; SEC("fentry/XXX") int BPF_PROG(fentry_XXX) { - struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; u32 key = bpf_get_smp_processor_id(); u32 i; @@ -54,10 +59,10 @@ int BPF_PROG(fentry_XXX) } for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { - struct bpf_perf_event_value reading; + struct bpf_perf_event_value___local reading; int err; - err = bpf_perf_event_read_value(&events, key, &reading, + err = bpf_perf_event_read_value(&events, key, (void *)&reading, sizeof(reading)); if (err) return 0; @@ -69,14 +74,14 @@ int BPF_PROG(fentry_XXX) } static inline void -fexit_update_maps(u32 id, struct bpf_perf_event_value *after) +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value___local *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ if (before && before->counter) { - struct bpf_perf_event_value *accum; + struct bpf_perf_event_value___local *accum; diff.counter = after->counter - before->counter; diff.enabled = after->enabled - before->enabled; @@ -94,16 +99,17 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after) SEC("fexit/XXX") int BPF_PROG(fexit_XXX) { - struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; /* read all events before updating the maps, to reduce error */ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, - readings + i, sizeof(*readings)); + (void *)(readings + i), + sizeof(*readings)); if (err) return 0; } @@ -116,4 +122,4 @@ int BPF_PROG(fexit_XXX) return 0; } -char LICENSE[] SEC("license") = "GPL"; +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/profiler.h b/tools/bpf/bpftool/skeleton/profiler.h deleted file mode 100644 index 1f767e9510f7..000000000000 --- a/tools/bpf/bpftool/skeleton/profiler.h +++ /dev/null @@ -1,46 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __PROFILER_H -#define __PROFILER_H - -/* useful typedefs from vmlinux.h */ - -typedef signed char __s8; -typedef unsigned char __u8; -typedef short int __s16; -typedef short unsigned int __u16; -typedef int __s32; -typedef unsigned int __u32; -typedef long long int __s64; -typedef long long unsigned int __u64; - -typedef __s8 s8; -typedef __u8 u8; -typedef __s16 s16; -typedef __u16 u16; -typedef __s32 s32; -typedef __u32 u32; -typedef __s64 s64; -typedef __u64 u64; - -enum { - false = 0, - true = 1, -}; - -#ifdef __CHECKER__ -#define __bitwise__ __attribute__((bitwise)) -#else -#define __bitwise__ -#endif - -typedef __u16 __bitwise__ __le16; -typedef __u16 __bitwise__ __be16; -typedef __u32 __bitwise__ __le32; -typedef __u32 __bitwise__ __be32; -typedef __u64 __bitwise__ __le64; -typedef __u64 __bitwise__ __be64; - -typedef __u16 __bitwise__ __sum16; -typedef __u32 __bitwise__ __wsum; - -#endif /* __PROFILER_H */ diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index b58b91f62ffb..d573f2640d8e 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -32,7 +32,7 @@ static const struct btf *get_btf_vmlinux(void) return btf_vmlinux; btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(btf_vmlinux)) + if (!btf_vmlinux) p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); return btf_vmlinux; @@ -45,7 +45,7 @@ static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) const char *st_ops_name; kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) + if (!kern_btf) return "<btf_vmlinux_not_found>"; t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); @@ -63,10 +63,8 @@ static __s32 get_map_info_type_id(void) return map_info_type_id; kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) { - map_info_type_id = PTR_ERR(kern_btf); - return map_info_type_id; - } + if (!kern_btf) + return 0; map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info", BTF_KIND_STRUCT); @@ -153,7 +151,7 @@ static int get_next_struct_ops_map(const char *name, int *res_fd, return -1; } - err = bpf_obj_get_info_by_fd(fd, info, &info_len); + err = bpf_map_get_info_by_fd(fd, info, &info_len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -252,7 +250,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, } fd = bpf_map_get_fd_by_id(id); - if (fd == -1) { + if (fd < 0) { p_err("can't get map by id (%lu): %s", id, strerror(errno)); res.nr_errs++; return res; @@ -264,7 +262,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, goto done; } - if (bpf_obj_get_info_by_fd(fd, info, &info_len)) { + if (bpf_map_get_info_by_fd(fd, info, &info_len)) { p_err("can't get map info: %s", strerror(errno)); res.nr_errs++; goto done; @@ -278,6 +276,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, res.nr_maps++; + if (wtr) + jsonw_start_array(wtr); + if (func(fd, info, data, wtr)) res.nr_errs++; else if (!wtr && json_output) @@ -290,6 +291,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, */ jsonw_null(json_wtr); + if (wtr) + jsonw_end_array(wtr); + done: free(info); close(fd); @@ -415,7 +419,7 @@ static int do_dump(int argc, char **argv) } kern_btf = get_btf_vmlinux(); - if (IS_ERR(kern_btf)) + if (!kern_btf) return -1; if (!json_output) { @@ -477,69 +481,111 @@ static int do_unregister(int argc, char **argv) return cmd_retval(&res, true); } +static int pin_link(struct bpf_link *link, const char *pindir, + const char *name) +{ + char pinfile[PATH_MAX]; + int err; + + err = pathname_concat(pinfile, sizeof(pinfile), pindir, name); + if (err) + return -1; + + return bpf_link__pin(link, pinfile); +} + static int do_register(int argc, char **argv) { - struct bpf_object_load_attr load_attr = {}; - const struct bpf_map_def *def; + LIBBPF_OPTS(bpf_object_open_opts, open_opts); + __u32 link_info_len = sizeof(struct bpf_link_info); + struct bpf_link_info link_info = {}; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); int nr_errs = 0, nr_maps = 0; + const char *linkdir = NULL; struct bpf_object *obj; struct bpf_link *link; struct bpf_map *map; const char *file; - if (argc != 1) + if (argc != 1 && argc != 2) usage(); file = GET_ARG(); + if (argc == 1) + linkdir = GET_ARG(); - obj = bpf_object__open(file); - if (IS_ERR_OR_NULL(obj)) + if (linkdir && mount_bpffs_for_pin(linkdir, true)) { + p_err("can't mount bpffs for pinning"); return -1; + } - set_max_rlimit(); - - load_attr.obj = obj; if (verifier_logs) /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (!obj) + return -1; + + set_max_rlimit(); - if (bpf_object__load_xattr(&load_attr)) { + if (bpf_object__load(obj)) { bpf_object__close(obj); return -1; } bpf_object__for_each_map(map, obj) { - def = bpf_map__def(map); - if (def->type != BPF_MAP_TYPE_STRUCT_OPS) + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) continue; link = bpf_map__attach_struct_ops(map); - if (IS_ERR(link)) { + if (!link) { p_err("can't register struct_ops %s: %s", - bpf_map__name(map), - strerror(-PTR_ERR(link))); + bpf_map__name(map), strerror(errno)); nr_errs++; continue; } nr_maps++; - bpf_link__disconnect(link); - bpf_link__destroy(link); - - if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, - &info_len)) - p_info("Registered %s %s id %u", - get_kern_struct_ops_name(&info), - bpf_map__name(map), - info.id); - else + if (bpf_map_get_info_by_fd(bpf_map__fd(map), &info, + &info_len)) { /* Not p_err. The struct_ops was attached * successfully. */ p_info("Registered %s but can't find id: %s", bpf_map__name(map), strerror(errno)); + goto clean_link; + } + if (!(bpf_map__map_flags(map) & BPF_F_LINK)) { + p_info("Registered %s %s id %u", + get_kern_struct_ops_name(&info), + info.name, + info.id); + goto clean_link; + } + if (bpf_link_get_info_by_fd(bpf_link__fd(link), + &link_info, + &link_info_len)) { + p_err("Registered %s but can't find link id: %s", + bpf_map__name(map), strerror(errno)); + nr_errs++; + goto clean_link; + } + if (linkdir && pin_link(link, linkdir, info.name)) { + p_err("can't pin link %u for %s: %s", + link_info.id, info.name, + strerror(errno)); + nr_errs++; + goto clean_link; + } + p_info("Registered %s %s map id %u link id %u", + get_kern_struct_ops_name(&info), + info.name, info.id, link_info.id); + +clean_link: + bpf_link__disconnect(link); + bpf_link__destroy(link); } bpf_object__close(obj); @@ -568,12 +614,12 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s { show | list } [STRUCT_OPS_MAP]\n" " %1$s %2$s dump [STRUCT_OPS_MAP]\n" - " %1$s %2$s register OBJ\n" + " %1$s %2$s register OBJ [LINK_DIR]\n" " %1$s %2$s unregister STRUCT_OPS_MAP\n" " %1$s %2$s help\n" "\n" - " OPTIONS := { {-j|--json} [{-p|--pretty}] }\n" " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n" + " " HELP_SPEC_OPTIONS " }\n" "", bin_name, argv[-2]); @@ -596,8 +642,7 @@ int do_struct_ops(int argc, char **argv) err = cmd_select(cmds, argc, argv, do_help); - if (!IS_ERR(btf_vmlinux)) - btf__free(btf_vmlinux); + btf__free(btf_vmlinux); return err; } diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c index e80a5c79b38f..bf1f02212797 100644 --- a/tools/bpf/bpftool/tracelog.c +++ b/tools/bpf/bpftool/tracelog.c @@ -9,7 +9,7 @@ #include <string.h> #include <unistd.h> #include <linux/magic.h> -#include <sys/fcntl.h> +#include <fcntl.h> #include <sys/vfs.h> #include "main.h" diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 8608cd68cdd0..567f56dfd9f1 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -1,13 +1,16 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2018 Netronome Systems, Inc. */ +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <stdarg.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/types.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include "disasm.h" #include "json_writer.h" @@ -32,8 +35,8 @@ void kernel_syms_load(struct dump_data *dd) return; while (fgets(buff, sizeof(buff), fp)) { - tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1, - sizeof(*dd->sym_mapping)); + tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); if (!tmp) { out: free(dd->sym_mapping); @@ -43,7 +46,11 @@ out: } dd->sym_mapping = tmp; sym = &dd->sym_mapping[dd->sym_count]; - if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + + /* module is optional */ + sym->module[0] = '\0'; + /* trim the square brackets around the module name */ + if (sscanf(buff, "%p %*c %s [%[^]]s", &address, sym->name, sym->module) < 2) continue; sym->address = (unsigned long)address; if (!strcmp(sym->name, "__bpf_call_base")) { @@ -196,6 +203,12 @@ static const char *print_imm(void *private_data, else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[idx:%u]+%u", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_FUNC) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "subprog[%+d]", insn->imm); else snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "0x%llx", (unsigned long long)full_imm); @@ -352,7 +365,8 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, } void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, - unsigned int start_idx) + unsigned int start_idx, + bool opcodes, bool linum) { const struct bpf_insn_cbs cbs = { .cb_print = print_insn_for_graph, @@ -360,14 +374,61 @@ void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, .cb_imm = print_imm, .private_data = dd, }; + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_line_info *last_linfo = NULL; + struct bpf_func_info *record = dd->func_info; struct bpf_insn *insn_start = buf_start; struct bpf_insn *insn_end = buf_end; struct bpf_insn *cur = insn_start; + struct btf *btf = dd->btf; + bool double_insn = false; + char func_sig[1024]; for (; cur <= insn_end; cur++) { - printf("% 4d: ", (int)(cur - insn_start + start_idx)); + unsigned int insn_off; + + if (double_insn) { + double_insn = false; + continue; + } + double_insn = cur->code == (BPF_LD | BPF_IMM | BPF_DW); + + insn_off = (unsigned int)(cur - insn_start + start_idx); + if (btf && record) { + if (record->insn_off == insn_off) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') + printf("; %s:\\l\\\n", func_sig); + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, insn_off, 0); + if (linfo && linfo != last_linfo) { + btf_dump_linfo_dotlabel(btf, linfo, linum); + last_linfo = linfo; + } + } + + printf("%d: ", insn_off); print_bpf_insn(&cbs, cur, true); + + if (opcodes) { + printf("\\ \\ \\ \\ "); + fprint_hex(stdout, cur, 8, " "); + if (double_insn && cur <= insn_end - 1) { + printf(" "); + fprint_hex(stdout, cur + 1, 8, " "); + } + printf("\\l\\\n"); + } + if (cur != insn_end) - printf(" | "); + printf("| "); } } diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h index 54847e174273..db3ba0671501 100644 --- a/tools/bpf/bpftool/xlated_dumper.h +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -5,12 +5,14 @@ #define __BPF_TOOL_XLATED_DUMPER_H #define SYM_MAX_NAME 256 +#define MODULE_MAX_NAME 64 struct bpf_prog_linfo; struct kernel_sym { unsigned long address; char name[SYM_MAX_NAME]; + char module[MODULE_MAX_NAME]; }; struct dump_data { @@ -34,6 +36,7 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, bool opcodes, bool linum); void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end, - unsigned int start_index); + unsigned int start_index, + bool opcodes, bool linum); #endif diff --git a/tools/bpf/resolve_btfids/.gitignore b/tools/bpf/resolve_btfids/.gitignore new file mode 100644 index 000000000000..52d5e9721d92 --- /dev/null +++ b/tools/bpf/resolve_btfids/.gitignore @@ -0,0 +1,4 @@ +/fixdep +/resolve_btfids +/libbpf/ +/libsubcmd/ diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build new file mode 100644 index 000000000000..077de3829c72 --- /dev/null +++ b/tools/bpf/resolve_btfids/Build @@ -0,0 +1,12 @@ +hostprogs := resolve_btfids + +resolve_btfids-y += main.o +resolve_btfids-y += rbtree.o +resolve_btfids-y += zalloc.o +resolve_btfids-y += string.o +resolve_btfids-y += ctype.o +resolve_btfids-y += str_error_r.o + +$(OUTPUT)%.o: ../../lib/%.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,host_cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile new file mode 100644 index 000000000000..4b8079f294f6 --- /dev/null +++ b/tools/bpf/resolve_btfids/Makefile @@ -0,0 +1,112 @@ +# SPDX-License-Identifier: GPL-2.0-only +include ../../scripts/Makefile.include +include ../../scripts/Makefile.arch + +srctree := $(abspath $(CURDIR)/../../../) + +ifeq ($(V),1) + Q = + msg = +else + Q = @ + ifeq ($(silent),1) + msg = + else + msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + endif + MAKEFLAGS=--no-print-directory +endif + +# Overrides for the prepare step libraries. +HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ + CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" + +RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar +CROSS_COMPILE = + +OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ + +LIBBPF_SRC := $(srctree)/tools/lib/bpf/ +SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ + +BPFOBJ := $(OUTPUT)/libbpf/libbpf.a +LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ +SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a +SUBCMD_OUT := $(abspath $(dir $(SUBCMDOBJ)))/ + +LIBBPF_DESTDIR := $(LIBBPF_OUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include + +SUBCMD_DESTDIR := $(SUBCMD_OUT) +SUBCMD_INCLUDE := $(SUBCMD_DESTDIR)include + +BINARY := $(OUTPUT)/resolve_btfids +BINARY_IN := $(BINARY)-in.o + +all: $(BINARY) + +prepare: $(BPFOBJ) $(SUBCMDOBJ) + +$(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT): + $(call msg,MKDIR,,$@) + $(Q)mkdir -p $(@) + +$(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd + $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(SUBCMD_OUT) \ + DESTDIR=$(SUBCMD_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ + $(abspath $@) install_headers + +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ + DESTDIR=$(LIBBPF_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ + $(abspath $@) install_headers + +LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) + +HOSTCFLAGS_resolve_btfids += -g \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(LIBBPF_INCLUDE) \ + -I$(SUBCMD_INCLUDE) \ + $(LIBELF_FLAGS) + +LIBS = $(LIBELF_LIBS) -lz + +export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR +include $(srctree)/tools/build/Makefile.include + +$(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) + $(Q)$(MAKE) $(build)=resolve_btfids + +$(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) + $(call msg,LINK,$@) + $(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) + +clean_objects := $(wildcard $(OUTPUT)/*.o \ + $(OUTPUT)/.*.o.cmd \ + $(OUTPUT)/.*.o.d \ + $(LIBBPF_OUT) \ + $(LIBBPF_DESTDIR) \ + $(SUBCMD_OUT) \ + $(SUBCMD_DESTDIR) \ + $(OUTPUT)/resolve_btfids) + +ifneq ($(clean_objects),) +clean: fixdep-clean + $(call msg,CLEAN,$(BINARY)) + $(Q)$(RM) -rf $(clean_objects) +else +clean: +endif + +tags: + $(call msg,GEN,,tags) + $(Q)ctags -R . $(LIBBPF_SRC) $(SUBCMD_SRC) + +FORCE: + +.PHONY: all FORCE clean tags prepare diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c new file mode 100644 index 000000000000..d9520cb826b3 --- /dev/null +++ b/tools/bpf/resolve_btfids/main.c @@ -0,0 +1,825 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * resolve_btfids scans ELF object for .BTF_ids section and resolves + * its symbols with BTF ID values. + * + * Each symbol points to 4 bytes data and is expected to have + * following name syntax: + * + * __BTF_ID__<type>__<symbol>[__<id>] + * + * type is: + * + * func - lookup BTF_KIND_FUNC symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__func__vfs_close__1: + * .zero 4 + * + * struct - lookup BTF_KIND_STRUCT symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__struct__sk_buff__1: + * .zero 4 + * + * union - lookup BTF_KIND_UNION symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__union__thread_union__1: + * .zero 4 + * + * typedef - lookup BTF_KIND_TYPEDEF symbol with <symbol> name + * and store its ID into the data: + * + * __BTF_ID__typedef__pid_t__1: + * .zero 4 + * + * set - store symbol size into first 4 bytes and sort following + * ID list + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__func__vfs_getattr__3: + * .zero 4 + * __BTF_ID__func__vfs_fallocate__4: + * .zero 4 + * + * set8 - store symbol size into first 4 bytes and sort following + * ID list + * + * __BTF_ID__set8__list: + * .zero 8 + * list: + * __BTF_ID__func__vfs_getattr__3: + * .zero 4 + * .word (1 << 0) | (1 << 2) + * __BTF_ID__func__vfs_fallocate__5: + * .zero 4 + * .word (1 << 3) | (1 << 1) | (1 << 2) + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <stdlib.h> +#include <libelf.h> +#include <gelf.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <linux/btf_ids.h> +#include <linux/rbtree.h> +#include <linux/zalloc.h> +#include <linux/err.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <subcmd/parse-options.h> + +#define BTF_IDS_SECTION ".BTF_ids" +#define BTF_ID_PREFIX "__BTF_ID__" + +#define BTF_STRUCT "struct" +#define BTF_UNION "union" +#define BTF_TYPEDEF "typedef" +#define BTF_FUNC "func" +#define BTF_SET "set" +#define BTF_SET8 "set8" + +#define ADDR_CNT 100 + +#if __BYTE_ORDER == __LITTLE_ENDIAN +# define ELFDATANATIVE ELFDATA2LSB +#elif __BYTE_ORDER == __BIG_ENDIAN +# define ELFDATANATIVE ELFDATA2MSB +#else +# error "Unknown machine endianness!" +#endif + +struct btf_id { + struct rb_node rb_node; + char *name; + union { + int id; + int cnt; + }; + int addr_cnt; + bool is_set; + bool is_set8; + Elf64_Addr addr[ADDR_CNT]; +}; + +struct object { + const char *path; + const char *btf; + const char *base_btf_path; + + struct { + int fd; + Elf *elf; + Elf_Data *symbols; + Elf_Data *idlist; + int symbols_shndx; + int idlist_shndx; + size_t strtabidx; + unsigned long idlist_addr; + int encoding; + } efile; + + struct rb_root sets; + struct rb_root structs; + struct rb_root unions; + struct rb_root typedefs; + struct rb_root funcs; + + int nr_funcs; + int nr_structs; + int nr_unions; + int nr_typedefs; +}; + +static int verbose; + +static int eprintf(int level, int var, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (var >= level) { + va_start(args, fmt); + ret = vfprintf(stderr, fmt, args); + va_end(args); + } + return ret; +} + +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_debug(fmt, ...) \ + eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) + +static bool is_btf_id(const char *name) +{ + return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1); +} + +static struct btf_id *btf_id__find(struct rb_root *root, const char *name) +{ + struct rb_node *p = root->rb_node; + struct btf_id *id; + int cmp; + + while (p) { + id = rb_entry(p, struct btf_id, rb_node); + cmp = strcmp(id->name, name); + if (cmp < 0) + p = p->rb_left; + else if (cmp > 0) + p = p->rb_right; + else + return id; + } + return NULL; +} + +static struct btf_id * +btf_id__add(struct rb_root *root, char *name, bool unique) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct btf_id *id; + int cmp; + + while (*p != NULL) { + parent = *p; + id = rb_entry(parent, struct btf_id, rb_node); + cmp = strcmp(id->name, name); + if (cmp < 0) + p = &(*p)->rb_left; + else if (cmp > 0) + p = &(*p)->rb_right; + else + return unique ? NULL : id; + } + + id = zalloc(sizeof(*id)); + if (id) { + pr_debug("adding symbol %s\n", name); + id->name = name; + rb_link_node(&id->rb_node, parent, p); + rb_insert_color(&id->rb_node, root); + } + return id; +} + +static char *get_id(const char *prefix_end) +{ + /* + * __BTF_ID__func__vfs_truncate__0 + * prefix_end = ^ + * pos = ^ + */ + int len = strlen(prefix_end); + int pos = sizeof("__") - 1; + char *p, *id; + + if (pos >= len) + return NULL; + + id = strdup(prefix_end + pos); + if (id) { + /* + * __BTF_ID__func__vfs_truncate__0 + * id = ^ + * + * cut the unique id part + */ + p = strrchr(id, '_'); + p--; + if (*p != '_') { + free(id); + return NULL; + } + *p = '\0'; + } + return id; +} + +static struct btf_id *add_set(struct object *obj, char *name, bool is_set8) +{ + /* + * __BTF_ID__set__name + * name = ^ + * id = ^ + */ + char *id = name + (is_set8 ? sizeof(BTF_SET8 "__") : sizeof(BTF_SET "__")) - 1; + int len = strlen(name); + + if (id >= name + len) { + pr_err("FAILED to parse set name: %s\n", name); + return NULL; + } + + return btf_id__add(&obj->sets, id, true); +} + +static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) +{ + char *id; + + id = get_id(name + size); + if (!id) { + pr_err("FAILED to parse symbol name: %s\n", name); + return NULL; + } + + return btf_id__add(root, id, false); +} + +/* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */ +#ifndef SHF_COMPRESSED +#define SHF_COMPRESSED (1 << 11) /* Section with compressed data. */ +#endif + +/* + * The data of compressed section should be aligned to 4 + * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld + * sets sh_addralign to 1, which makes libelf fail with + * misaligned section error during the update: + * FAILED elf_update(WRITE): invalid section alignment + * + * While waiting for ld fix, we fix the compressed sections + * sh_addralign value manualy. + */ +static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh) +{ + int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8; + + if (!(sh->sh_flags & SHF_COMPRESSED)) + return 0; + + if (sh->sh_addralign == expected) + return 0; + + pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n", + sh->sh_addralign, expected); + + sh->sh_addralign = expected; + + if (gelf_update_shdr(scn, sh) == 0) { + pr_err("FAILED cannot update section header: %s\n", + elf_errmsg(-1)); + return -1; + } + return 0; +} + +static int elf_collect(struct object *obj) +{ + Elf_Scn *scn = NULL; + size_t shdrstrndx; + GElf_Ehdr ehdr; + int idx = 0; + Elf *elf; + int fd; + + fd = open(obj->path, O_RDWR, 0666); + if (fd == -1) { + pr_err("FAILED cannot open %s: %s\n", + obj->path, strerror(errno)); + return -1; + } + + elf_version(EV_CURRENT); + + elf = elf_begin(fd, ELF_C_RDWR_MMAP, NULL); + if (!elf) { + close(fd); + pr_err("FAILED cannot create ELF descriptor: %s\n", + elf_errmsg(-1)); + return -1; + } + + obj->efile.fd = fd; + obj->efile.elf = elf; + + elf_flagelf(elf, ELF_C_SET, ELF_F_LAYOUT); + + if (elf_getshdrstrndx(elf, &shdrstrndx) != 0) { + pr_err("FAILED cannot get shdr str ndx\n"); + return -1; + } + + if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) { + pr_err("FAILED cannot get ELF header: %s\n", + elf_errmsg(-1)); + return -1; + } + obj->efile.encoding = ehdr.e_ident[EI_DATA]; + + /* + * Scan all the elf sections and look for save data + * from .BTF_ids section and symbols. + */ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + Elf_Data *data; + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_err("FAILED get section(%d) header\n", idx); + return -1; + } + + name = elf_strptr(elf, shdrstrndx, sh.sh_name); + if (!name) { + pr_err("FAILED get section(%d) name\n", idx); + return -1; + } + + data = elf_getdata(scn, 0); + if (!data) { + pr_err("FAILED to get section(%d) data from %s\n", + idx, name); + return -1; + } + + pr_debug2("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + idx, name, (unsigned long) data->d_size, + (int) sh.sh_link, (unsigned long) sh.sh_flags, + (int) sh.sh_type); + + if (sh.sh_type == SHT_SYMTAB) { + obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; + obj->efile.strtabidx = sh.sh_link; + } else if (!strcmp(name, BTF_IDS_SECTION)) { + obj->efile.idlist = data; + obj->efile.idlist_shndx = idx; + obj->efile.idlist_addr = sh.sh_addr; + } + + if (compressed_section_fix(elf, scn, &sh)) + return -1; + } + + return 0; +} + +static int symbols_collect(struct object *obj) +{ + Elf_Scn *scn = NULL; + int n, i; + GElf_Shdr sh; + char *name; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -1; + + if (gelf_getshdr(scn, &sh) != &sh) + return -1; + + n = sh.sh_size / sh.sh_entsize; + + /* + * Scan symbols and look for the ones starting with + * __BTF_ID__* over .BTF_ids section. + */ + for (i = 0; i < n; i++) { + char *prefix; + struct btf_id *id; + GElf_Sym sym; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -1; + + if (sym.st_shndx != obj->efile.idlist_shndx) + continue; + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + + if (!is_btf_id(name)) + continue; + + /* + * __BTF_ID__TYPE__vfs_truncate__0 + * prefix = ^ + */ + prefix = name + sizeof(BTF_ID_PREFIX) - 1; + + /* struct */ + if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) { + obj->nr_structs++; + id = add_symbol(&obj->structs, prefix, sizeof(BTF_STRUCT) - 1); + /* union */ + } else if (!strncmp(prefix, BTF_UNION, sizeof(BTF_UNION) - 1)) { + obj->nr_unions++; + id = add_symbol(&obj->unions, prefix, sizeof(BTF_UNION) - 1); + /* typedef */ + } else if (!strncmp(prefix, BTF_TYPEDEF, sizeof(BTF_TYPEDEF) - 1)) { + obj->nr_typedefs++; + id = add_symbol(&obj->typedefs, prefix, sizeof(BTF_TYPEDEF) - 1); + /* func */ + } else if (!strncmp(prefix, BTF_FUNC, sizeof(BTF_FUNC) - 1)) { + obj->nr_funcs++; + id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1); + /* set8 */ + } else if (!strncmp(prefix, BTF_SET8, sizeof(BTF_SET8) - 1)) { + id = add_set(obj, prefix, true); + /* + * SET8 objects store list's count, which is encoded + * in symbol's size, together with 'cnt' field hence + * that - 1. + */ + if (id) { + id->cnt = sym.st_size / sizeof(uint64_t) - 1; + id->is_set8 = true; + } + /* set */ + } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { + id = add_set(obj, prefix, false); + /* + * SET objects store list's count, which is encoded + * in symbol's size, together with 'cnt' field hence + * that - 1. + */ + if (id) { + id->cnt = sym.st_size / sizeof(int) - 1; + id->is_set = true; + } + } else { + pr_err("FAILED unsupported prefix %s\n", prefix); + return -1; + } + + if (!id) + return -ENOMEM; + + if (id->addr_cnt >= ADDR_CNT) { + pr_err("FAILED symbol %s crossed the number of allowed lists\n", + id->name); + return -1; + } + id->addr[id->addr_cnt++] = sym.st_value; + } + + return 0; +} + +static int symbols_resolve(struct object *obj) +{ + int nr_typedefs = obj->nr_typedefs; + int nr_structs = obj->nr_structs; + int nr_unions = obj->nr_unions; + int nr_funcs = obj->nr_funcs; + struct btf *base_btf = NULL; + int err, type_id; + struct btf *btf; + __u32 nr_types; + + if (obj->base_btf_path) { + base_btf = btf__parse(obj->base_btf_path, NULL); + err = libbpf_get_error(base_btf); + if (err) { + pr_err("FAILED: load base BTF from %s: %s\n", + obj->base_btf_path, strerror(-err)); + return -1; + } + } + + btf = btf__parse_split(obj->btf ?: obj->path, base_btf); + err = libbpf_get_error(btf); + if (err) { + pr_err("FAILED: load BTF from %s: %s\n", + obj->btf ?: obj->path, strerror(-err)); + goto out; + } + + err = -1; + nr_types = btf__type_cnt(btf); + + /* + * Iterate all the BTF types and search for collected symbol IDs. + */ + for (type_id = 1; type_id < nr_types; type_id++) { + const struct btf_type *type; + struct rb_root *root; + struct btf_id *id; + const char *str; + int *nr; + + type = btf__type_by_id(btf, type_id); + if (!type) { + pr_err("FAILED: malformed BTF, can't resolve type for ID %d\n", + type_id); + goto out; + } + + if (btf_is_func(type) && nr_funcs) { + nr = &nr_funcs; + root = &obj->funcs; + } else if (btf_is_struct(type) && nr_structs) { + nr = &nr_structs; + root = &obj->structs; + } else if (btf_is_union(type) && nr_unions) { + nr = &nr_unions; + root = &obj->unions; + } else if (btf_is_typedef(type) && nr_typedefs) { + nr = &nr_typedefs; + root = &obj->typedefs; + } else + continue; + + str = btf__name_by_offset(btf, type->name_off); + if (!str) { + pr_err("FAILED: malformed BTF, can't resolve name for ID %d\n", + type_id); + goto out; + } + + id = btf_id__find(root, str); + if (id) { + if (id->id) { + pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n", + str, id->id, type_id, id->id); + } else { + id->id = type_id; + (*nr)--; + } + } + } + + err = 0; +out: + btf__free(base_btf); + btf__free(btf); + return err; +} + +static int id_patch(struct object *obj, struct btf_id *id) +{ + Elf_Data *data = obj->efile.idlist; + int *ptr = data->d_buf; + int i; + + /* For set, set8, id->id may be 0 */ + if (!id->id && !id->is_set && !id->is_set8) + pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); + + for (i = 0; i < id->addr_cnt; i++) { + unsigned long addr = id->addr[i]; + unsigned long idx = addr - obj->efile.idlist_addr; + + pr_debug("patching addr %5lu: ID %7d [%s]\n", + idx, id->id, id->name); + + if (idx >= data->d_size) { + pr_err("FAILED patching index %lu out of bounds %lu\n", + idx, data->d_size); + return -1; + } + + idx = idx / sizeof(int); + ptr[idx] = id->id; + } + + return 0; +} + +static int __symbols_patch(struct object *obj, struct rb_root *root) +{ + struct rb_node *next; + struct btf_id *id; + + next = rb_first(root); + while (next) { + id = rb_entry(next, struct btf_id, rb_node); + + if (id_patch(obj, id)) + return -1; + + next = rb_next(next); + } + return 0; +} + +static int cmp_id(const void *pa, const void *pb) +{ + const int *a = pa, *b = pb; + + return *a - *b; +} + +static int sets_patch(struct object *obj) +{ + Elf_Data *data = obj->efile.idlist; + struct rb_node *next; + + next = rb_first(&obj->sets); + while (next) { + struct btf_id_set8 *set8; + struct btf_id_set *set; + unsigned long addr, off; + struct btf_id *id; + + id = rb_entry(next, struct btf_id, rb_node); + addr = id->addr[0]; + off = addr - obj->efile.idlist_addr; + + /* sets are unique */ + if (id->addr_cnt != 1) { + pr_err("FAILED malformed data for set '%s'\n", + id->name); + return -1; + } + + if (id->is_set) { + set = data->d_buf + off; + qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id); + } else { + set8 = data->d_buf + off; + /* + * Make sure id is at the beginning of the pairs + * struct, otherwise the below qsort would not work. + */ + BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id); + qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id); + + /* + * When ELF endianness does not match endianness of the + * host, libelf will do the translation when updating + * the ELF. This, however, corrupts SET8 flags which are + * already in the target endianness. So, let's bswap + * them to the host endianness and libelf will then + * correctly translate everything. + */ + if (obj->efile.encoding != ELFDATANATIVE) { + int i; + + set8->flags = bswap_32(set8->flags); + for (i = 0; i < set8->cnt; i++) { + set8->pairs[i].flags = + bswap_32(set8->pairs[i].flags); + } + } + } + + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", + off, id->is_set ? set->cnt : set8->cnt, id->name); + + next = rb_next(next); + } + return 0; +} + +static int symbols_patch(struct object *obj) +{ + int err; + + if (__symbols_patch(obj, &obj->structs) || + __symbols_patch(obj, &obj->unions) || + __symbols_patch(obj, &obj->typedefs) || + __symbols_patch(obj, &obj->funcs) || + __symbols_patch(obj, &obj->sets)) + return -1; + + if (sets_patch(obj)) + return -1; + + /* Set type to ensure endian translation occurs. */ + obj->efile.idlist->d_type = ELF_T_WORD; + + elf_flagdata(obj->efile.idlist, ELF_C_SET, ELF_F_DIRTY); + + err = elf_update(obj->efile.elf, ELF_C_WRITE); + if (err < 0) { + pr_err("FAILED elf_update(WRITE): %s\n", + elf_errmsg(-1)); + } + + pr_debug("update %s for %s\n", + err >= 0 ? "ok" : "failed", obj->path); + return err < 0 ? -1 : 0; +} + +static const char * const resolve_btfids_usage[] = { + "resolve_btfids [<options>] <ELF object>", + NULL +}; + +int main(int argc, const char **argv) +{ + struct object obj = { + .efile = { + .idlist_shndx = -1, + .symbols_shndx = -1, + }, + .structs = RB_ROOT, + .unions = RB_ROOT, + .typedefs = RB_ROOT, + .funcs = RB_ROOT, + .sets = RB_ROOT, + }; + struct option btfid_options[] = { + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show errors, etc)"), + OPT_STRING(0, "btf", &obj.btf, "BTF data", + "BTF data"), + OPT_STRING('b', "btf_base", &obj.base_btf_path, "file", + "path of file providing base BTF"), + OPT_END() + }; + int err = -1; + + argc = parse_options(argc, argv, btfid_options, resolve_btfids_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc != 1) + usage_with_options(resolve_btfids_usage, btfid_options); + + obj.path = argv[0]; + + if (elf_collect(&obj)) + goto out; + + /* + * We did not find .BTF_ids section or symbols section, + * nothing to do.. + */ + if (obj.efile.idlist_shndx == -1 || + obj.efile.symbols_shndx == -1) { + pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n"); + err = 0; + goto out; + } + + if (symbols_collect(&obj)) + goto out; + + if (symbols_resolve(&obj)) + goto out; + + if (symbols_patch(&obj)) + goto out; + + err = 0; +out: + if (obj.efile.elf) { + elf_end(obj.efile.elf); + close(obj.efile.fd); + } + return err; +} diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index fb1337d69868..d8288936c912 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -1,85 +1,92 @@ # 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 +include ../../scripts/Makefile.include + +OUTPUT ?= $(abspath .output)/ + +BPFTOOL_OUTPUT := $(OUTPUT)bpftool/ +DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bootstrap/bpftool BPFTOOL ?= $(DEFAULT_BPFTOOL) LIBBPF_SRC := $(abspath ../../lib/bpf) -BPFOBJ := $(OUTPUT)/libbpf.a -BPF_INCLUDE := $(OUTPUT) -INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) \ - -I$(abspath ../../include/uapi) -CFLAGS := -g -Wall +BPFOBJ_OUTPUT := $(OUTPUT)libbpf/ +BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a +BPF_DESTDIR := $(BPFOBJ_OUTPUT) +BPF_INCLUDE := $(BPF_DESTDIR)/include +INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) +CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) +CFLAGS += $(EXTRA_CFLAGS) +LDFLAGS += $(EXTRA_LDFLAGS) # 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_PATHS := $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../vmlinux /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 +.PHONY: all clean runqslower libbpf_hdrs all: runqslower runqslower: $(OUTPUT)/runqslower clean: - $(call msg,CLEAN) - $(Q)rm -rf $(OUTPUT) runqslower + $(call QUIET_CLEAN, runqslower) + $(Q)$(RM) -r $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT) + $(Q)$(RM) $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h + $(Q)$(RM) $(OUTPUT)runqslower + $(Q)$(RM) -r .output + +libbpf_hdrs: $(BPFOBJ) $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) - $(call msg,BINARY,$@) - $(Q)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ + $(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ - $(OUTPUT)/runqslower.bpf.o + $(OUTPUT)/runqslower.bpf.o | libbpf_hdrs -$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h +$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h | libbpf_hdrs $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) - $(call msg,GEN-SKEL,$@) - $(Q)$(BPFTOOL) gen skeleton $< > $@ + $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@ $(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) - $(call msg,BPF,$@) - $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + $(QUIET_GEN)$(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 $@ + $(QUIET_CC)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@ -$(OUTPUT): - $(call msg,MKDIR,$@) - $(Q)mkdir -p $(OUTPUT) +$(OUTPUT) $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT): + $(QUIET_MKDIR)mkdir -p $@ $(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) - $(call msg,GEN,$@) +ifeq ($(VMLINUX_H),) $(Q)if [ ! -e "$(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 > $@ + $(QUIET_GEN)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ +else + $(Q)cp "$(VMLINUX_H)" $@ +endif -$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ - OUTPUT=$(abspath $(dir $@))/ $(abspath $@) +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \ + DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers -$(DEFAULT_BPFTOOL): - $(Q)$(MAKE) $(submake_extras) -C ../bpftool \ - prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install +$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) bootstrap diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index 1f18a409f044..9a5c1f008fe6 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -11,9 +11,9 @@ 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); + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); __type(value, u64); } start SEC(".maps"); @@ -25,15 +25,20 @@ struct { /* record enqueue timestamp */ __always_inline -static int trace_enqueue(u32 tgid, u32 pid) +static int trace_enqueue(struct task_struct *t) { - u64 ts; + u32 pid = t->pid; + u64 *ptr; if (!pid || (targ_pid && targ_pid != pid)) return 0; - ts = bpf_ktime_get_ns(); - bpf_map_update_elem(&start, &pid, &ts, 0); + ptr = bpf_task_storage_get(&start, t, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + *ptr = bpf_ktime_get_ns(); return 0; } @@ -43,7 +48,7 @@ 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); + return trace_enqueue(p); } SEC("tp_btf/sched_wakeup_new") @@ -52,7 +57,7 @@ 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); + return trace_enqueue(p); } SEC("tp_btf/sched_switch") @@ -63,19 +68,23 @@ int handle__sched_switch(u64 *ctx) */ struct task_struct *prev = (struct task_struct *)ctx[1]; struct task_struct *next = (struct task_struct *)ctx[2]; - struct event event = {}; + struct runq_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); + if (prev->__state == TASK_RUNNING) + trace_enqueue(prev); pid = next->pid; + /* For pid mismatch, save a bpf_task_storage_get */ + if (!pid || (targ_pid && targ_pid != pid)) + return 0; + /* fetch timestamp and calculate delta */ - tsp = bpf_map_lookup_elem(&start, &pid); + tsp = bpf_task_storage_get(&start, next, 0, 0); if (!tsp) return 0; /* missed enqueue */ @@ -91,7 +100,7 @@ int handle__sched_switch(u64 *ctx) bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, &event, sizeof(event)); - bpf_map_delete_elem(&start, &pid); + bpf_task_storage_delete(&start, next); return 0; } diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c index d89715844952..83c5993a139a 100644 --- a/tools/bpf/runqslower/runqslower.c +++ b/tools/bpf/runqslower/runqslower.c @@ -4,7 +4,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <sys/resource.h> #include <time.h> #include <bpf/libbpf.h> #include <bpf/bpf.h> @@ -88,19 +87,9 @@ int libbpf_print_fn(enum libbpf_print_level level, 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; + const struct runq_event *e = data; struct tm *tm; char ts[32]; time_t t; @@ -123,7 +112,6 @@ int main(int argc, char **argv) .parser = parse_arg, .doc = argp_program_doc, }; - struct perf_buffer_opts pb_opts; struct perf_buffer *pb = NULL; struct runqslower_bpf *obj; int err; @@ -134,11 +122,8 @@ int main(int argc, char **argv) libbpf_set_print(libbpf_print_fn); - err = bump_memlock_rlimit(); - if (err) { - fprintf(stderr, "failed to increase rlimit: %d", err); - return 1; - } + /* Use libbpf 1.0 API mode */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); obj = runqslower_bpf__open(); if (!obj) { @@ -165,9 +150,8 @@ int main(int argc, char **argv) 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); + pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, + handle_event, handle_lost_events, NULL, NULL); err = libbpf_get_error(pb); if (err) { pb = NULL; diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h index 9db225425e5f..4f70f07200c2 100644 --- a/tools/bpf/runqslower/runqslower.h +++ b/tools/bpf/runqslower/runqslower.h @@ -4,7 +4,7 @@ #define TASK_COMM_LEN 16 -struct event { +struct runq_event { char task[TASK_COMM_LEN]; __u64 delta_us; pid_t pid; |