diff options
| author | Joel Fernandes <joelagnelf@nvidia.com> | 2026-07-18 13:15:36 -0400 |
|---|---|---|
| committer | Paul E. McKenney <paulmck@kernel.org> | 2026-07-23 10:39:57 -0700 |
| commit | 34ff636f322c6d5e4f0a52338fa63a7dff09a495 (patch) | |
| tree | 7629759c1ec7148b95bc8ab3080df20a5ecd2273 /tools/bpf | |
| download | linux-stable-34ff636f322c6d5e4f0a52338fa63a7dff09a495.tar.gz linux-stable-34ff636f322c6d5e4f0a52338fa63a7dff09a495.zip | |
scftorture: Count single_rpc offline failures in statistics outputgrafted
scf_torture_stats_print() aggregates each invoker thread's counters
into a local scf_statistics structure before printing, but the
n_single_rpc_ofl field is missing from the aggregation loop. As a
result, the "single_rpc_ofl" value printed in the statistics line is
always zero, even when smp_call_function_single() invocations for the
RPC test have failed due to offline CPUs and been counted by the
invoker threads.
Add the missing accumulation so that the printed value reflects the
actual counts.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Diffstat (limited to 'tools/bpf')
62 files changed, 28836 insertions, 0 deletions
diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore new file mode 100644 index 000000000..cf5334217 --- /dev/null +++ b/tools/bpf/.gitignore @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +FEATURE-DUMP.bpf +feature +bpf_asm +bpf_dbg +bpf_exp.yacc.* +bpf_jit_disasm diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile new file mode 100644 index 000000000..9c19e81f3 --- /dev/null +++ b/tools/bpf/Makefile @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: GPL-2.0 +include ../scripts/Makefile.include + +prefix ?= /usr/local + +LEX = flex +YACC = bison +MAKE = make +INSTALL ?= install + +CFLAGS += -Wall -O2 +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/include +CFLAGS += $(EXTRA_CFLAGS) + +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is set to ".". building_out_of_srctree is undefined for in srctree +# builds +ifeq ($(srctree),) +update_srctree := 1 +endif +ifndef building_out_of_srctree +update_srctree := 1 +endif +ifeq ($(update_srctree),1) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +FEATURE_USER = .bpf +FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled +FEATURE_DISPLAY = libbfd + +check_feat := 1 +NON_CHECK_FEAT_TARGETS := clean bpftool_clean resolve_btfids_clean +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) + check_feat := 0 +endif +endif + +ifeq ($(check_feat),1) +ifeq ($(FEATURES_DUMP),) +include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif +endif + +ifeq ($(feature-disassembler-four-args), 1) +CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE +endif +ifeq ($(feature-disassembler-init-styled), 1) +CFLAGS += -DDISASM_INIT_STYLED +endif + +$(OUTPUT)%.yacc.c: $(srctree)/tools/bpf/%.y + $(QUIET_BISON)$(YACC) -o $@ -d $< + +$(OUTPUT)%.lex.c: $(srctree)/tools/bpf/%.l + $(QUIET_FLEX)$(LEX) -o $@ $< + +$(OUTPUT)%.o: $(srctree)/tools/bpf/%.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $< + +$(OUTPUT)%.yacc.o: $(OUTPUT)%.yacc.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $< +$(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -o $@ $< + +PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm + +all: $(PROGS) bpftool + +$(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm' +$(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ -lopcodes -lbfd -ldl + +$(OUTPUT)bpf_dbg: $(OUTPUT)bpf_dbg.o + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ -lreadline + +$(OUTPUT)bpf_asm: $(OUTPUT)bpf_asm.o $(OUTPUT)bpf_exp.yacc.o $(OUTPUT)bpf_exp.lex.o + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ + +$(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 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.* + $(call QUIET_CLEAN, core-gen) + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf + $(Q)$(RM) -r -- $(OUTPUT)feature + +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 + $(call QUIET_INSTALL, bpf_dbg) + $(Q)$(INSTALL) $(OUTPUT)bpf_dbg $(DESTDIR)$(prefix)/bin/bpf_dbg + $(call QUIET_INSTALL, bpf_asm) + $(Q)$(INSTALL) $(OUTPUT)bpf_asm $(DESTDIR)$(prefix)/bin/bpf_asm + +bpftool: + $(call descend,bpftool) + +bpftool_install: + $(call descend,bpftool,install) + +bpftool_clean: + $(call descend,bpftool,clean) + +resolve_btfids: + $(call descend,resolve_btfids) + +resolve_btfids_clean: + $(call descend,resolve_btfids,clean) + +.PHONY: all install clean bpftool bpftool_install bpftool_clean \ + resolve_btfids resolve_btfids_clean diff --git a/tools/bpf/bpf_asm.c b/tools/bpf/bpf_asm.c new file mode 100644 index 000000000..0063c3c02 --- /dev/null +++ b/tools/bpf/bpf_asm.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Minimal BPF assembler + * + * Instead of libpcap high-level filter expressions, it can be quite + * useful to define filters in low-level BPF assembler (that is kept + * close to Steven McCanne and Van Jacobson's original BPF paper). + * In particular for BPF JIT implementors, JIT security auditors, or + * just for defining BPF expressions that contain extensions which are + * not supported by compilers. + * + * How to get into it: + * + * 1) read Documentation/networking/filter.rst + * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary + * blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will + * pretty print a C-like construct. + * + * Copyright 2013 Daniel Borkmann <borkmann@redhat.com> + */ + +#include <stdbool.h> +#include <stdio.h> +#include <string.h> + +extern void bpf_asm_compile(FILE *fp, bool cstyle); + +int main(int argc, char **argv) +{ + FILE *fp = stdin; + bool cstyle = false; + int i; + + for (i = 1; i < argc; i++) { + if (!strncmp("-c", argv[i], 2)) { + cstyle = true; + continue; + } + + fp = fopen(argv[i], "r"); + if (!fp) { + fp = stdin; + continue; + } + + break; + } + + bpf_asm_compile(fp, cstyle); + + return 0; +} diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c new file mode 100644 index 000000000..00e560a17 --- /dev/null +++ b/tools/bpf/bpf_dbg.c @@ -0,0 +1,1398 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Minimal BPF debugger + * + * Minimal BPF debugger that mimics the kernel's engine (w/o extensions) + * and allows for single stepping through selected packets from a pcap + * with a provided user filter in order to facilitate verification of a + * BPF program. Besides others, this is useful to verify BPF programs + * before attaching to a live system, and can be used in socket filters, + * cls_bpf, xt_bpf, team driver and e.g. PTP code; in particular when a + * single more complex BPF program is being used. Reasons for a more + * complex BPF program are likely primarily to optimize execution time + * for making a verdict when multiple simple BPF programs are combined + * into one in order to prevent parsing same headers multiple times. + * + * More on how to debug BPF opcodes see Documentation/networking/filter.rst + * which is the main document on BPF. Mini howto for getting started: + * + * 1) `./bpf_dbg` to enter the shell (shell cmds denoted with '>'): + * 2) > load bpf 6,40 0 0 12,21 0 3 20... (output from `bpf_asm` or + * `tcpdump -iem1 -ddd port 22 | tr '\n' ','` to load as filter) + * 3) > load pcap foo.pcap + * 4) > run <n>/disassemble/dump/quit (self-explanatory) + * 5) > breakpoint 2 (sets bp at loaded BPF insns 2, do `run` then; + * multiple bps can be set, of course, a call to `breakpoint` + * w/o args shows currently loaded bps, `breakpoint reset` for + * resetting all breakpoints) + * 6) > select 3 (`run` etc will start from the 3rd packet in the pcap) + * 7) > step [-<n>, +<n>] (performs single stepping through the BPF) + * + * Copyright 2013 Daniel Borkmann <borkmann@redhat.com> + */ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <ctype.h> +#include <stdbool.h> +#include <stdarg.h> +#include <setjmp.h> +#include <linux/filter.h> +#include <linux/if_packet.h> +#include <readline/readline.h> +#include <readline/history.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <fcntl.h> +#include <errno.h> +#include <signal.h> +#include <arpa/inet.h> +#include <net/ethernet.h> + +#define TCPDUMP_MAGIC 0xa1b2c3d4 + +#define BPF_LDX_B (BPF_LDX | BPF_B) +#define BPF_LDX_W (BPF_LDX | BPF_W) +#define BPF_JMP_JA (BPF_JMP | BPF_JA) +#define BPF_JMP_JEQ (BPF_JMP | BPF_JEQ) +#define BPF_JMP_JGT (BPF_JMP | BPF_JGT) +#define BPF_JMP_JGE (BPF_JMP | BPF_JGE) +#define BPF_JMP_JSET (BPF_JMP | BPF_JSET) +#define BPF_ALU_ADD (BPF_ALU | BPF_ADD) +#define BPF_ALU_SUB (BPF_ALU | BPF_SUB) +#define BPF_ALU_MUL (BPF_ALU | BPF_MUL) +#define BPF_ALU_DIV (BPF_ALU | BPF_DIV) +#define BPF_ALU_MOD (BPF_ALU | BPF_MOD) +#define BPF_ALU_NEG (BPF_ALU | BPF_NEG) +#define BPF_ALU_AND (BPF_ALU | BPF_AND) +#define BPF_ALU_OR (BPF_ALU | BPF_OR) +#define BPF_ALU_XOR (BPF_ALU | BPF_XOR) +#define BPF_ALU_LSH (BPF_ALU | BPF_LSH) +#define BPF_ALU_RSH (BPF_ALU | BPF_RSH) +#define BPF_MISC_TAX (BPF_MISC | BPF_TAX) +#define BPF_MISC_TXA (BPF_MISC | BPF_TXA) +#define BPF_LD_B (BPF_LD | BPF_B) +#define BPF_LD_H (BPF_LD | BPF_H) +#define BPF_LD_W (BPF_LD | BPF_W) + +#ifndef array_size +# define array_size(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#ifndef __check_format_printf +# define __check_format_printf(pos_fmtstr, pos_fmtargs) \ + __attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs)))) +#endif + +enum { + CMD_OK, + CMD_ERR, + CMD_EX, +}; + +struct shell_cmd { + const char *name; + int (*func)(char *args); +}; + +struct pcap_filehdr { + uint32_t magic; + uint16_t version_major; + uint16_t version_minor; + int32_t thiszone; + uint32_t sigfigs; + uint32_t snaplen; + uint32_t linktype; +}; + +struct pcap_timeval { + int32_t tv_sec; + int32_t tv_usec; +}; + +struct pcap_pkthdr { + struct pcap_timeval ts; + uint32_t caplen; + uint32_t len; +}; + +struct bpf_regs { + uint32_t A; + uint32_t X; + uint32_t M[BPF_MEMWORDS]; + uint32_t R; + bool Rs; + uint16_t Pc; +}; + +static struct sock_filter bpf_image[BPF_MAXINSNS + 1]; +static unsigned int bpf_prog_len; + +static int bpf_breakpoints[64]; +static struct bpf_regs bpf_regs[BPF_MAXINSNS + 1]; +static struct bpf_regs bpf_curr; +static unsigned int bpf_regs_len; + +static int pcap_fd = -1; +static unsigned int pcap_packet; +static size_t pcap_map_size; +static char *pcap_ptr_va_start, *pcap_ptr_va_curr; + +static const char * const op_table[] = { + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_LD_B] = "ldb", + [BPF_LD_H] = "ldh", + [BPF_LD_W] = "ld", + [BPF_LDX] = "ldx", + [BPF_LDX_B] = "ldxb", + [BPF_JMP_JA] = "ja", + [BPF_JMP_JEQ] = "jeq", + [BPF_JMP_JGT] = "jgt", + [BPF_JMP_JGE] = "jge", + [BPF_JMP_JSET] = "jset", + [BPF_ALU_ADD] = "add", + [BPF_ALU_SUB] = "sub", + [BPF_ALU_MUL] = "mul", + [BPF_ALU_DIV] = "div", + [BPF_ALU_MOD] = "mod", + [BPF_ALU_NEG] = "neg", + [BPF_ALU_AND] = "and", + [BPF_ALU_OR] = "or", + [BPF_ALU_XOR] = "xor", + [BPF_ALU_LSH] = "lsh", + [BPF_ALU_RSH] = "rsh", + [BPF_MISC_TAX] = "tax", + [BPF_MISC_TXA] = "txa", + [BPF_RET] = "ret", +}; + +static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...) +{ + int ret; + va_list vl; + + va_start(vl, fmt); + ret = vfprintf(rl_outstream, fmt, vl); + va_end(vl); + + return ret; +} + +static int matches(const char *cmd, const char *pattern) +{ + int len = strlen(cmd); + + if (len > strlen(pattern)) + return -1; + + return memcmp(pattern, cmd, len); +} + +static void hex_dump(const uint8_t *buf, size_t len) +{ + int i; + + rl_printf("%3u: ", 0); + for (i = 0; i < len; i++) { + if (i && !(i % 16)) + rl_printf("\n%3u: ", i); + rl_printf("%02x ", buf[i]); + } + rl_printf("\n"); +} + +static bool bpf_prog_loaded(void) +{ + if (bpf_prog_len == 0) + rl_printf("no bpf program loaded!\n"); + + return bpf_prog_len > 0; +} + +static void bpf_disasm(const struct sock_filter f, unsigned int i) +{ + const char *op, *fmt; + int val = f.k; + char buf[256]; + + switch (f.code) { + case BPF_RET | BPF_K: + op = op_table[BPF_RET]; + fmt = "#%#x"; + break; + case BPF_RET | BPF_A: + op = op_table[BPF_RET]; + fmt = "a"; + break; + case BPF_RET | BPF_X: + op = op_table[BPF_RET]; + fmt = "x"; + break; + case BPF_MISC_TAX: + op = op_table[BPF_MISC_TAX]; + fmt = ""; + break; + case BPF_MISC_TXA: + op = op_table[BPF_MISC_TXA]; + fmt = ""; + break; + case BPF_ST: + op = op_table[BPF_ST]; + fmt = "M[%d]"; + break; + case BPF_STX: + op = op_table[BPF_STX]; + fmt = "M[%d]"; + break; + case BPF_LD_W | BPF_ABS: + op = op_table[BPF_LD_W]; + fmt = "[%d]"; + break; + case BPF_LD_H | BPF_ABS: + op = op_table[BPF_LD_H]; + fmt = "[%d]"; + break; + case BPF_LD_B | BPF_ABS: + op = op_table[BPF_LD_B]; + fmt = "[%d]"; + break; + case BPF_LD_W | BPF_LEN: + op = op_table[BPF_LD_W]; + fmt = "#len"; + break; + case BPF_LD_W | BPF_IND: + op = op_table[BPF_LD_W]; + fmt = "[x+%d]"; + break; + case BPF_LD_H | BPF_IND: + op = op_table[BPF_LD_H]; + fmt = "[x+%d]"; + break; + case BPF_LD_B | BPF_IND: + op = op_table[BPF_LD_B]; + fmt = "[x+%d]"; + break; + case BPF_LD | BPF_IMM: + op = op_table[BPF_LD_W]; + fmt = "#%#x"; + break; + case BPF_LDX | BPF_IMM: + op = op_table[BPF_LDX]; + fmt = "#%#x"; + break; + case BPF_LDX_B | BPF_MSH: + op = op_table[BPF_LDX_B]; + fmt = "4*([%d]&0xf)"; + break; + case BPF_LD | BPF_MEM: + op = op_table[BPF_LD_W]; + fmt = "M[%d]"; + break; + case BPF_LDX | BPF_MEM: + op = op_table[BPF_LDX]; + fmt = "M[%d]"; + break; + case BPF_JMP_JA: + op = op_table[BPF_JMP_JA]; + fmt = "%d"; + val = i + 1 + f.k; + break; + case BPF_JMP_JGT | BPF_X: + op = op_table[BPF_JMP_JGT]; + fmt = "x"; + break; + case BPF_JMP_JGT | BPF_K: + op = op_table[BPF_JMP_JGT]; + fmt = "#%#x"; + break; + case BPF_JMP_JGE | BPF_X: + op = op_table[BPF_JMP_JGE]; + fmt = "x"; + break; + case BPF_JMP_JGE | BPF_K: + op = op_table[BPF_JMP_JGE]; + fmt = "#%#x"; + break; + case BPF_JMP_JEQ | BPF_X: + op = op_table[BPF_JMP_JEQ]; + fmt = "x"; + break; + case BPF_JMP_JEQ | BPF_K: + op = op_table[BPF_JMP_JEQ]; + fmt = "#%#x"; + break; + case BPF_JMP_JSET | BPF_X: + op = op_table[BPF_JMP_JSET]; + fmt = "x"; + break; + case BPF_JMP_JSET | BPF_K: + op = op_table[BPF_JMP_JSET]; + fmt = "#%#x"; + break; + case BPF_ALU_NEG: + op = op_table[BPF_ALU_NEG]; + fmt = ""; + break; + case BPF_ALU_LSH | BPF_X: + op = op_table[BPF_ALU_LSH]; + fmt = "x"; + break; + case BPF_ALU_LSH | BPF_K: + op = op_table[BPF_ALU_LSH]; + fmt = "#%d"; + break; + case BPF_ALU_RSH | BPF_X: + op = op_table[BPF_ALU_RSH]; + fmt = "x"; + break; + case BPF_ALU_RSH | BPF_K: + op = op_table[BPF_ALU_RSH]; + fmt = "#%d"; + break; + case BPF_ALU_ADD | BPF_X: + op = op_table[BPF_ALU_ADD]; + fmt = "x"; + break; + case BPF_ALU_ADD | BPF_K: + op = op_table[BPF_ALU_ADD]; + fmt = "#%d"; + break; + case BPF_ALU_SUB | BPF_X: + op = op_table[BPF_ALU_SUB]; + fmt = "x"; + break; + case BPF_ALU_SUB | BPF_K: + op = op_table[BPF_ALU_SUB]; + fmt = "#%d"; + break; + case BPF_ALU_MUL | BPF_X: + op = op_table[BPF_ALU_MUL]; + fmt = "x"; + break; + case BPF_ALU_MUL | BPF_K: + op = op_table[BPF_ALU_MUL]; + fmt = "#%d"; + break; + case BPF_ALU_DIV | BPF_X: + op = op_table[BPF_ALU_DIV]; + fmt = "x"; + break; + case BPF_ALU_DIV | BPF_K: + op = op_table[BPF_ALU_DIV]; + fmt = "#%d"; + break; + case BPF_ALU_MOD | BPF_X: + op = op_table[BPF_ALU_MOD]; + fmt = "x"; + break; + case BPF_ALU_MOD | BPF_K: + op = op_table[BPF_ALU_MOD]; + fmt = "#%d"; + break; + case BPF_ALU_AND | BPF_X: + op = op_table[BPF_ALU_AND]; + fmt = "x"; + break; + case BPF_ALU_AND | BPF_K: + op = op_table[BPF_ALU_AND]; + fmt = "#%#x"; + break; + case BPF_ALU_OR | BPF_X: + op = op_table[BPF_ALU_OR]; + fmt = "x"; + break; + case BPF_ALU_OR | BPF_K: + op = op_table[BPF_ALU_OR]; + fmt = "#%#x"; + break; + case BPF_ALU_XOR | BPF_X: + op = op_table[BPF_ALU_XOR]; + fmt = "x"; + break; + case BPF_ALU_XOR | BPF_K: + op = op_table[BPF_ALU_XOR]; + fmt = "#%#x"; + break; + default: + op = "nosup"; + fmt = "%#x"; + val = f.code; + break; + } + + memset(buf, 0, sizeof(buf)); + snprintf(buf, sizeof(buf), fmt, val); + buf[sizeof(buf) - 1] = 0; + + if ((BPF_CLASS(f.code) == BPF_JMP && BPF_OP(f.code) != BPF_JA)) + rl_printf("l%d:\t%s %s, l%d, l%d\n", i, op, buf, + i + 1 + f.jt, i + 1 + f.jf); + else + rl_printf("l%d:\t%s %s\n", i, op, buf); +} + +static void bpf_dump_curr(struct bpf_regs *r, struct sock_filter *f) +{ + int i, m = 0; + + rl_printf("pc: [%u]\n", r->Pc); + rl_printf("code: [%u] jt[%u] jf[%u] k[%u]\n", + f->code, f->jt, f->jf, f->k); + rl_printf("curr: "); + bpf_disasm(*f, r->Pc); + + if (f->jt || f->jf) { + rl_printf("jt: "); + bpf_disasm(*(f + f->jt + 1), r->Pc + f->jt + 1); + rl_printf("jf: "); + bpf_disasm(*(f + f->jf + 1), r->Pc + f->jf + 1); + } + + rl_printf("A: [%#08x][%u]\n", r->A, r->A); + rl_printf("X: [%#08x][%u]\n", r->X, r->X); + if (r->Rs) + rl_printf("ret: [%#08x][%u]!\n", r->R, r->R); + + for (i = 0; i < BPF_MEMWORDS; i++) { + if (r->M[i]) { + m++; + rl_printf("M[%d]: [%#08x][%u]\n", i, r->M[i], r->M[i]); + } + } + if (m == 0) + rl_printf("M[0,%d]: [%#08x][%u]\n", BPF_MEMWORDS - 1, 0, 0); +} + +static void bpf_dump_pkt(uint8_t *pkt, uint32_t pkt_caplen, uint32_t pkt_len) +{ + if (pkt_caplen != pkt_len) + rl_printf("cap: %u, len: %u\n", pkt_caplen, pkt_len); + else + rl_printf("len: %u\n", pkt_len); + + hex_dump(pkt, pkt_caplen); +} + +static void bpf_disasm_all(const struct sock_filter *f, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len; i++) + bpf_disasm(f[i], i); +} + +static void bpf_dump_all(const struct sock_filter *f, unsigned int len) +{ + unsigned int i; + + rl_printf("/* { op, jt, jf, k }, */\n"); + for (i = 0; i < len; i++) + rl_printf("{ %#04x, %2u, %2u, %#010x },\n", + f[i].code, f[i].jt, f[i].jf, f[i].k); +} + +static bool bpf_runnable(struct sock_filter *f, unsigned int len) +{ + int sock, ret, i; + struct sock_fprog bpf = { + .filter = f, + .len = len, + }; + + sock = socket(AF_INET, SOCK_DGRAM, 0); + if (sock < 0) { + rl_printf("cannot open socket!\n"); + return false; + } + ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf)); + close(sock); + if (ret < 0) { + rl_printf("program not allowed to run by kernel!\n"); + return false; + } + for (i = 0; i < len; i++) { + if (BPF_CLASS(f[i].code) == BPF_LD && + f[i].k > SKF_AD_OFF) { + rl_printf("extensions currently not supported!\n"); + return false; + } + } + + return true; +} + +static void bpf_reset_breakpoints(void) +{ + int i; + + for (i = 0; i < array_size(bpf_breakpoints); i++) + bpf_breakpoints[i] = -1; +} + +static void bpf_set_breakpoints(unsigned int where) +{ + int i; + bool set = false; + + for (i = 0; i < array_size(bpf_breakpoints); i++) { + if (bpf_breakpoints[i] == (int) where) { + rl_printf("breakpoint already set!\n"); + set = true; + break; + } + + if (bpf_breakpoints[i] == -1 && set == false) { + bpf_breakpoints[i] = where; + set = true; + } + } + + if (!set) + rl_printf("too many breakpoints set, reset first!\n"); +} + +static void bpf_dump_breakpoints(void) +{ + int i; + + rl_printf("breakpoints: "); + + for (i = 0; i < array_size(bpf_breakpoints); i++) { + if (bpf_breakpoints[i] < 0) + continue; + rl_printf("%d ", bpf_breakpoints[i]); + } + + rl_printf("\n"); +} + +static void bpf_reset(void) +{ + bpf_regs_len = 0; + + memset(bpf_regs, 0, sizeof(bpf_regs)); + memset(&bpf_curr, 0, sizeof(bpf_curr)); +} + +static void bpf_safe_regs(void) +{ + memcpy(&bpf_regs[bpf_regs_len++], &bpf_curr, sizeof(bpf_curr)); +} + +static bool bpf_restore_regs(int off) +{ + unsigned int index = bpf_regs_len - 1 + off; + + if (index == 0) { + bpf_reset(); + return true; + } else if (index < bpf_regs_len) { + memcpy(&bpf_curr, &bpf_regs[index], sizeof(bpf_curr)); + bpf_regs_len = index; + return true; + } else { + rl_printf("reached bottom of register history stack!\n"); + return false; + } +} + +static uint32_t extract_u32(uint8_t *pkt, uint32_t off) +{ + uint32_t r; + + memcpy(&r, &pkt[off], sizeof(r)); + + return ntohl(r); +} + +static uint16_t extract_u16(uint8_t *pkt, uint32_t off) +{ + uint16_t r; + + memcpy(&r, &pkt[off], sizeof(r)); + + return ntohs(r); +} + +static uint8_t extract_u8(uint8_t *pkt, uint32_t off) +{ + return pkt[off]; +} + +static void set_return(struct bpf_regs *r) +{ + r->R = 0; + r->Rs = true; +} + +static void bpf_single_step(struct bpf_regs *r, struct sock_filter *f, + uint8_t *pkt, uint32_t pkt_caplen, + uint32_t pkt_len) +{ + uint32_t K = f->k; + int d; + + switch (f->code) { + case BPF_RET | BPF_K: + r->R = K; + r->Rs = true; + break; + case BPF_RET | BPF_A: + r->R = r->A; + r->Rs = true; + break; + case BPF_RET | BPF_X: + r->R = r->X; + r->Rs = true; + break; + case BPF_MISC_TAX: + r->X = r->A; + break; + case BPF_MISC_TXA: + r->A = r->X; + break; + case BPF_ST: + r->M[K] = r->A; + break; + case BPF_STX: + r->M[K] = r->X; + break; + case BPF_LD_W | BPF_ABS: + d = pkt_caplen - K; + if (d >= sizeof(uint32_t)) + r->A = extract_u32(pkt, K); + else + set_return(r); + break; + case BPF_LD_H | BPF_ABS: + d = pkt_caplen - K; + if (d >= sizeof(uint16_t)) + r->A = extract_u16(pkt, K); + else + set_return(r); + break; + case BPF_LD_B | BPF_ABS: + d = pkt_caplen - K; + if (d >= sizeof(uint8_t)) + r->A = extract_u8(pkt, K); + else + set_return(r); + break; + case BPF_LD_W | BPF_IND: + d = pkt_caplen - (r->X + K); + if (d >= sizeof(uint32_t)) + r->A = extract_u32(pkt, r->X + K); + break; + case BPF_LD_H | BPF_IND: + d = pkt_caplen - (r->X + K); + if (d >= sizeof(uint16_t)) + r->A = extract_u16(pkt, r->X + K); + else + set_return(r); + break; + case BPF_LD_B | BPF_IND: + d = pkt_caplen - (r->X + K); + if (d >= sizeof(uint8_t)) + r->A = extract_u8(pkt, r->X + K); + else + set_return(r); + break; + case BPF_LDX_B | BPF_MSH: + d = pkt_caplen - K; + if (d >= sizeof(uint8_t)) { + r->X = extract_u8(pkt, K); + r->X = (r->X & 0xf) << 2; + } else + set_return(r); + break; + case BPF_LD_W | BPF_LEN: + r->A = pkt_len; + break; + case BPF_LDX_W | BPF_LEN: + r->A = pkt_len; + break; + case BPF_LD | BPF_IMM: + r->A = K; + break; + case BPF_LDX | BPF_IMM: + r->X = K; + break; + case BPF_LD | BPF_MEM: + r->A = r->M[K]; + break; + case BPF_LDX | BPF_MEM: + r->X = r->M[K]; + break; + case BPF_JMP_JA: + r->Pc += K; + break; + case BPF_JMP_JGT | BPF_X: + r->Pc += r->A > r->X ? f->jt : f->jf; + break; + case BPF_JMP_JGT | BPF_K: + r->Pc += r->A > K ? f->jt : f->jf; + break; + case BPF_JMP_JGE | BPF_X: + r->Pc += r->A >= r->X ? f->jt : f->jf; + break; + case BPF_JMP_JGE | BPF_K: + r->Pc += r->A >= K ? f->jt : f->jf; + break; + case BPF_JMP_JEQ | BPF_X: + r->Pc += r->A == r->X ? f->jt : f->jf; + break; + case BPF_JMP_JEQ | BPF_K: + r->Pc += r->A == K ? f->jt : f->jf; + break; + case BPF_JMP_JSET | BPF_X: + r->Pc += r->A & r->X ? f->jt : f->jf; + break; + case BPF_JMP_JSET | BPF_K: + r->Pc += r->A & K ? f->jt : f->jf; + break; + case BPF_ALU_NEG: + r->A = -r->A; + break; + case BPF_ALU_LSH | BPF_X: + r->A <<= r->X; + break; + case BPF_ALU_LSH | BPF_K: + r->A <<= K; + break; + case BPF_ALU_RSH | BPF_X: + r->A >>= r->X; + break; + case BPF_ALU_RSH | BPF_K: + r->A >>= K; + break; + case BPF_ALU_ADD | BPF_X: + r->A += r->X; + break; + case BPF_ALU_ADD | BPF_K: + r->A += K; + break; + case BPF_ALU_SUB | BPF_X: + r->A -= r->X; + break; + case BPF_ALU_SUB | BPF_K: + r->A -= K; + break; + case BPF_ALU_MUL | BPF_X: + r->A *= r->X; + break; + case BPF_ALU_MUL | BPF_K: + r->A *= K; + break; + case BPF_ALU_DIV | BPF_X: + case BPF_ALU_MOD | BPF_X: + if (r->X == 0) { + set_return(r); + break; + } + goto do_div; + case BPF_ALU_DIV | BPF_K: + case BPF_ALU_MOD | BPF_K: + if (K == 0) { + set_return(r); + break; + } +do_div: + switch (f->code) { + case BPF_ALU_DIV | BPF_X: + r->A /= r->X; + break; + case BPF_ALU_DIV | BPF_K: + r->A /= K; + break; + case BPF_ALU_MOD | BPF_X: + r->A %= r->X; + break; + case BPF_ALU_MOD | BPF_K: + r->A %= K; + break; + } + break; + case BPF_ALU_AND | BPF_X: + r->A &= r->X; + break; + case BPF_ALU_AND | BPF_K: + r->A &= K; + break; + case BPF_ALU_OR | BPF_X: + r->A |= r->X; + break; + case BPF_ALU_OR | BPF_K: + r->A |= K; + break; + case BPF_ALU_XOR | BPF_X: + r->A ^= r->X; + break; + case BPF_ALU_XOR | BPF_K: + r->A ^= K; + break; + } +} + +static bool bpf_pc_has_breakpoint(uint16_t pc) +{ + int i; + + for (i = 0; i < array_size(bpf_breakpoints); i++) { + if (bpf_breakpoints[i] < 0) + continue; + if (bpf_breakpoints[i] == pc) + return true; + } + + return false; +} + +static bool bpf_handle_breakpoint(struct bpf_regs *r, struct sock_filter *f, + uint8_t *pkt, uint32_t pkt_caplen, + uint32_t pkt_len) +{ + rl_printf("-- register dump --\n"); + bpf_dump_curr(r, &f[r->Pc]); + rl_printf("-- packet dump --\n"); + bpf_dump_pkt(pkt, pkt_caplen, pkt_len); + rl_printf("(breakpoint)\n"); + return true; +} + +static int bpf_run_all(struct sock_filter *f, uint16_t bpf_len, uint8_t *pkt, + uint32_t pkt_caplen, uint32_t pkt_len) +{ + bool stop = false; + + while (bpf_curr.Rs == false && stop == false) { + bpf_safe_regs(); + + if (bpf_pc_has_breakpoint(bpf_curr.Pc)) + stop = bpf_handle_breakpoint(&bpf_curr, f, pkt, + pkt_caplen, pkt_len); + + bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen, + pkt_len); + bpf_curr.Pc++; + } + + return stop ? -1 : bpf_curr.R; +} + +static int bpf_run_stepping(struct sock_filter *f, uint16_t bpf_len, + uint8_t *pkt, uint32_t pkt_caplen, + uint32_t pkt_len, int next) +{ + bool stop = false; + int i = 1; + + while (!bpf_curr.Rs && !stop) { + bpf_safe_regs(); + + if (i++ == next) + stop = bpf_handle_breakpoint(&bpf_curr, f, pkt, + pkt_caplen, pkt_len); + + bpf_single_step(&bpf_curr, &f[bpf_curr.Pc], pkt, pkt_caplen, + pkt_len); + bpf_curr.Pc++; + } + + return stop ? -1 : bpf_curr.R; +} + +static bool pcap_loaded(void) +{ + if (pcap_fd < 0) + rl_printf("no pcap file loaded!\n"); + + return pcap_fd >= 0; +} + +static struct pcap_pkthdr *pcap_curr_pkt(void) +{ + return (void *) pcap_ptr_va_curr; +} + +static bool pcap_next_pkt(void) +{ + struct pcap_pkthdr *hdr = pcap_curr_pkt(); + + if (pcap_ptr_va_curr + sizeof(*hdr) - + pcap_ptr_va_start >= pcap_map_size) + return false; + if (hdr->caplen == 0 || hdr->len == 0 || hdr->caplen > hdr->len) + return false; + if (pcap_ptr_va_curr + sizeof(*hdr) + hdr->caplen - + pcap_ptr_va_start >= pcap_map_size) + return false; + + pcap_ptr_va_curr += (sizeof(*hdr) + hdr->caplen); + return true; +} + +static void pcap_reset_pkt(void) +{ + pcap_ptr_va_curr = pcap_ptr_va_start + sizeof(struct pcap_filehdr); +} + +static int try_load_pcap(const char *file) +{ + struct pcap_filehdr *hdr; + struct stat sb; + int ret; + + pcap_fd = open(file, O_RDONLY); + if (pcap_fd < 0) { + rl_printf("cannot open pcap [%s]!\n", strerror(errno)); + return CMD_ERR; + } + + ret = fstat(pcap_fd, &sb); + if (ret < 0) { + rl_printf("cannot fstat pcap file!\n"); + return CMD_ERR; + } + + if (!S_ISREG(sb.st_mode)) { + rl_printf("not a regular pcap file, duh!\n"); + return CMD_ERR; + } + + pcap_map_size = sb.st_size; + if (pcap_map_size <= sizeof(struct pcap_filehdr)) { + rl_printf("pcap file too small!\n"); + return CMD_ERR; + } + + pcap_ptr_va_start = mmap(NULL, pcap_map_size, PROT_READ, + MAP_SHARED | MAP_LOCKED, pcap_fd, 0); + if (pcap_ptr_va_start == MAP_FAILED) { + rl_printf("mmap of file failed!"); + return CMD_ERR; + } + + hdr = (void *) pcap_ptr_va_start; + if (hdr->magic != TCPDUMP_MAGIC) { + rl_printf("wrong pcap magic!\n"); + return CMD_ERR; + } + + pcap_reset_pkt(); + + return CMD_OK; + +} + +static void try_close_pcap(void) +{ + if (pcap_fd >= 0) { + munmap(pcap_ptr_va_start, pcap_map_size); + close(pcap_fd); + + pcap_ptr_va_start = pcap_ptr_va_curr = NULL; + pcap_map_size = 0; + pcap_packet = 0; + pcap_fd = -1; + } +} + +static int cmd_load_bpf(char *bpf_string) +{ + char sp, *token, separator = ','; + unsigned short bpf_len, i = 0; + struct sock_filter tmp; + + bpf_prog_len = 0; + memset(bpf_image, 0, sizeof(bpf_image)); + + if (sscanf(bpf_string, "%hu%c", &bpf_len, &sp) != 2 || + sp != separator || bpf_len > BPF_MAXINSNS || bpf_len == 0) { + rl_printf("syntax error in head length encoding!\n"); + return CMD_ERR; + } + + token = bpf_string; + while ((token = strchr(token, separator)) && (++token)[0]) { + if (i >= bpf_len) { + rl_printf("program exceeds encoded length!\n"); + return CMD_ERR; + } + + if (sscanf(token, "%hu %hhu %hhu %u,", + &tmp.code, &tmp.jt, &tmp.jf, &tmp.k) != 4) { + rl_printf("syntax error at instruction %d!\n", i); + return CMD_ERR; + } + + bpf_image[i].code = tmp.code; + bpf_image[i].jt = tmp.jt; + bpf_image[i].jf = tmp.jf; + bpf_image[i].k = tmp.k; + + i++; + } + + if (i != bpf_len) { + rl_printf("syntax error exceeding encoded length!\n"); + return CMD_ERR; + } else + bpf_prog_len = bpf_len; + if (!bpf_runnable(bpf_image, bpf_prog_len)) + bpf_prog_len = 0; + + return CMD_OK; +} + +static int cmd_load_pcap(char *file) +{ + char *file_trim, *tmp; + + file_trim = strtok_r(file, " ", &tmp); + if (file_trim == NULL) + return CMD_ERR; + + try_close_pcap(); + + return try_load_pcap(file_trim); +} + +static int cmd_load(char *arg) +{ + char *subcmd, *cont = NULL, *tmp = strdup(arg); + int ret = CMD_OK; + + subcmd = strtok_r(tmp, " ", &cont); + if (subcmd == NULL) + goto out; + if (matches(subcmd, "bpf") == 0) { + bpf_reset(); + bpf_reset_breakpoints(); + + if (!cont) + ret = CMD_ERR; + else + ret = cmd_load_bpf(cont); + } else if (matches(subcmd, "pcap") == 0) { + ret = cmd_load_pcap(cont); + } else { +out: + rl_printf("bpf <code>: load bpf code\n"); + rl_printf("pcap <file>: load pcap file\n"); + ret = CMD_ERR; + } + + free(tmp); + return ret; +} + +static int cmd_step(char *num) +{ + struct pcap_pkthdr *hdr; + int steps, ret; + + if (!bpf_prog_loaded() || !pcap_loaded()) + return CMD_ERR; + + steps = strtol(num, NULL, 10); + if (steps == 0 || strlen(num) == 0) + steps = 1; + if (steps < 0) { + if (!bpf_restore_regs(steps)) + return CMD_ERR; + steps = 1; + } + + hdr = pcap_curr_pkt(); + ret = bpf_run_stepping(bpf_image, bpf_prog_len, + (uint8_t *) hdr + sizeof(*hdr), + hdr->caplen, hdr->len, steps); + if (ret >= 0 || bpf_curr.Rs) { + bpf_reset(); + if (!pcap_next_pkt()) { + rl_printf("(going back to first packet)\n"); + pcap_reset_pkt(); + } else { + rl_printf("(next packet)\n"); + } + } + + return CMD_OK; +} + +static int cmd_select(char *num) +{ + unsigned int which, i; + bool have_next = true; + + if (!pcap_loaded() || strlen(num) == 0) + return CMD_ERR; + + which = strtoul(num, NULL, 10); + if (which == 0) { + rl_printf("packet count starts with 1, clamping!\n"); + which = 1; + } + + pcap_reset_pkt(); + bpf_reset(); + + for (i = 0; i < which && (have_next = pcap_next_pkt()); i++) + /* noop */; + if (!have_next || pcap_curr_pkt() == NULL) { + rl_printf("no packet #%u available!\n", which); + pcap_reset_pkt(); + return CMD_ERR; + } + + return CMD_OK; +} + +static int cmd_breakpoint(char *subcmd) +{ + if (!bpf_prog_loaded()) + return CMD_ERR; + if (strlen(subcmd) == 0) + bpf_dump_breakpoints(); + else if (matches(subcmd, "reset") == 0) + bpf_reset_breakpoints(); + else { + unsigned int where = strtoul(subcmd, NULL, 10); + + if (where < bpf_prog_len) { + bpf_set_breakpoints(where); + rl_printf("breakpoint at: "); + bpf_disasm(bpf_image[where], where); + } + } + + return CMD_OK; +} + +static int cmd_run(char *num) +{ + static uint32_t pass, fail; + bool has_limit = true; + int pkts = 0, i = 0; + + if (!bpf_prog_loaded() || !pcap_loaded()) + return CMD_ERR; + + pkts = strtol(num, NULL, 10); + if (pkts == 0 || strlen(num) == 0) + has_limit = false; + + do { + struct pcap_pkthdr *hdr = pcap_curr_pkt(); + int ret = bpf_run_all(bpf_image, bpf_prog_len, + (uint8_t *) hdr + sizeof(*hdr), + hdr->caplen, hdr->len); + if (ret > 0) + pass++; + else if (ret == 0) + fail++; + else + return CMD_OK; + bpf_reset(); + } while (pcap_next_pkt() && (!has_limit || (++i < pkts))); + + rl_printf("bpf passes:%u fails:%u\n", pass, fail); + + pcap_reset_pkt(); + bpf_reset(); + + pass = fail = 0; + return CMD_OK; +} + +static int cmd_disassemble(char *line_string) +{ + bool single_line = false; + unsigned long line; + + if (!bpf_prog_loaded()) + return CMD_ERR; + if (strlen(line_string) > 0 && + (line = strtoul(line_string, NULL, 10)) < bpf_prog_len) + single_line = true; + if (single_line) + bpf_disasm(bpf_image[line], line); + else + bpf_disasm_all(bpf_image, bpf_prog_len); + + return CMD_OK; +} + +static int cmd_dump(char *dontcare) +{ + if (!bpf_prog_loaded()) + return CMD_ERR; + + bpf_dump_all(bpf_image, bpf_prog_len); + + return CMD_OK; +} + +static int cmd_quit(char *dontcare) +{ + return CMD_EX; +} + +static const struct shell_cmd cmds[] = { + { .name = "load", .func = cmd_load }, + { .name = "select", .func = cmd_select }, + { .name = "step", .func = cmd_step }, + { .name = "run", .func = cmd_run }, + { .name = "breakpoint", .func = cmd_breakpoint }, + { .name = "disassemble", .func = cmd_disassemble }, + { .name = "dump", .func = cmd_dump }, + { .name = "quit", .func = cmd_quit }, +}; + +static int execf(char *arg) +{ + char *cmd, *cont, *tmp = strdup(arg); + int i, ret = 0, len; + + cmd = strtok_r(tmp, " ", &cont); + if (cmd == NULL) + goto out; + len = strlen(cmd); + for (i = 0; i < array_size(cmds); i++) { + if (len != strlen(cmds[i].name)) + continue; + if (strncmp(cmds[i].name, cmd, len) == 0) { + ret = cmds[i].func(cont); + break; + } + } +out: + free(tmp); + return ret; +} + +static char *shell_comp_gen(const char *buf, int state) +{ + static int list_index, len; + + if (!state) { + list_index = 0; + len = strlen(buf); + } + + for (; list_index < array_size(cmds); ) { + const char *name = cmds[list_index].name; + + list_index++; + if (strncmp(name, buf, len) == 0) + return strdup(name); + } + + return NULL; +} + +static char **shell_completion(const char *buf, int start, int end) +{ + char **matches = NULL; + + if (start == 0) + matches = rl_completion_matches(buf, shell_comp_gen); + + return matches; +} + +static void intr_shell(int sig) +{ + if (rl_end) + rl_kill_line(-1, 0); + + rl_crlf(); + rl_refresh_line(0, 0); + rl_free_line_state(); +} + +static void init_shell(FILE *fin, FILE *fout) +{ + char file[128]; + + snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME")); + read_history(file); + + rl_instream = fin; + rl_outstream = fout; + + rl_readline_name = "bpf_dbg"; + rl_terminal_name = getenv("TERM"); + + rl_catch_signals = 0; + rl_catch_sigwinch = 1; + + rl_attempted_completion_function = shell_completion; + + rl_bind_key('\t', rl_complete); + + rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap); + rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap); + + snprintf(file, sizeof(file), "%s/.bpf_dbg_init", getenv("HOME")); + rl_read_init_file(file); + + rl_prep_terminal(0); + rl_set_signals(); + + signal(SIGINT, intr_shell); +} + +static void exit_shell(FILE *fin, FILE *fout) +{ + char file[128]; + + snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME")); + write_history(file); + + clear_history(); + rl_deprep_terminal(); + + try_close_pcap(); + + if (fin != stdin) + fclose(fin); + if (fout != stdout) + fclose(fout); +} + +static int run_shell_loop(FILE *fin, FILE *fout) +{ + char *buf; + + init_shell(fin, fout); + + while ((buf = readline("> ")) != NULL) { + int ret = execf(buf); + if (ret == CMD_EX) + break; + if (ret == CMD_OK && strlen(buf) > 0) + add_history(buf); + + free(buf); + } + + exit_shell(fin, fout); + return 0; +} + +int main(int argc, char **argv) +{ + FILE *fin = NULL, *fout = NULL; + + if (argc >= 2) + fin = fopen(argv[1], "r"); + if (argc >= 3) + fout = fopen(argv[2], "w"); + + return run_shell_loop(fin ? : stdin, fout ? : stdout); +} diff --git a/tools/bpf/bpf_exp.l b/tools/bpf/bpf_exp.l new file mode 100644 index 000000000..4da8d053d --- /dev/null +++ b/tools/bpf/bpf_exp.l @@ -0,0 +1,198 @@ +/* + * BPF asm code lexer + * + * This program is free software; you can distribute it and/or modify + * it under the terms of the GNU General Public License as published + * by the Free Software Foundation; either version 2 of the License, + * or (at your option) any later version. + * + * Syntax kept close to: + * + * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new + * architecture for user-level packet capture. In Proceedings of the + * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993 + * Conference Proceedings (USENIX'93). USENIX Association, Berkeley, + * CA, USA, 2-2. + * + * Copyright 2013 Daniel Borkmann <borkmann@redhat.com> + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +%{ + +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> + +#include <linux/filter.h> + +#include "bpf_exp.yacc.h" + +extern void yyerror(const char *str); + +%} + +%option align +%option ecs + +%option nounput +%option noreject +%option noinput +%option noyywrap + +%option 8bit +%option caseless +%option yylineno + +%% + +"ldb" { return OP_LDB; } +"ldh" { return OP_LDH; } +"ld" { return OP_LD; } +"ldi" { return OP_LDI; } +"ldx" { return OP_LDX; } +"ldxi" { return OP_LDXI; } +"ldxb" { return OP_LDXB; } +"st" { return OP_ST; } +"stx" { return OP_STX; } +"jmp" { return OP_JMP; } +"ja" { return OP_JMP; } +"jeq" { return OP_JEQ; } +"jneq" { return OP_JNEQ; } +"jne" { return OP_JNEQ; } +"jlt" { return OP_JLT; } +"jle" { return OP_JLE; } +"jgt" { return OP_JGT; } +"jge" { return OP_JGE; } +"jset" { return OP_JSET; } +"add" { return OP_ADD; } +"sub" { return OP_SUB; } +"mul" { return OP_MUL; } +"div" { return OP_DIV; } +"mod" { return OP_MOD; } +"neg" { return OP_NEG; } +"and" { return OP_AND; } +"xor" { return OP_XOR; } +"or" { return OP_OR; } +"lsh" { return OP_LSH; } +"rsh" { return OP_RSH; } +"ret" { return OP_RET; } +"tax" { return OP_TAX; } +"txa" { return OP_TXA; } + +"#"?("len") { return K_PKT_LEN; } + +"#"?("proto") { + yylval.number = SKF_AD_PROTOCOL; + return extension; + } +"#"?("type") { + yylval.number = SKF_AD_PKTTYPE; + return extension; + } +"#"?("poff") { + yylval.number = SKF_AD_PAY_OFFSET; + return extension; + } +"#"?("ifidx") { + yylval.number = SKF_AD_IFINDEX; + return extension; + } +"#"?("nla") { + yylval.number = SKF_AD_NLATTR; + return extension; + } +"#"?("nlan") { + yylval.number = SKF_AD_NLATTR_NEST; + return extension; + } +"#"?("mark") { + yylval.number = SKF_AD_MARK; + return extension; + } +"#"?("queue") { + yylval.number = SKF_AD_QUEUE; + return extension; + } +"#"?("hatype") { + yylval.number = SKF_AD_HATYPE; + return extension; + } +"#"?("rxhash") { + yylval.number = SKF_AD_RXHASH; + return extension; + } +"#"?("cpu") { + yylval.number = SKF_AD_CPU; + return extension; + } +"#"?("vlan_tci") { + yylval.number = SKF_AD_VLAN_TAG; + return extension; + } +"#"?("vlan_pr") { + yylval.number = SKF_AD_VLAN_TAG_PRESENT; + return extension; + } +"#"?("vlan_avail") { + yylval.number = SKF_AD_VLAN_TAG_PRESENT; + return extension; + } +"#"?("vlan_tpid") { + yylval.number = SKF_AD_VLAN_TPID; + return extension; + } +"#"?("rand") { + yylval.number = SKF_AD_RANDOM; + return extension; + } + +":" { return ':'; } +"," { return ','; } +"#" { return '#'; } +"%" { return '%'; } +"[" { return '['; } +"]" { return ']'; } +"(" { return '('; } +")" { return ')'; } +"x" { return 'x'; } +"a" { return 'a'; } +"+" { return '+'; } +"M" { return 'M'; } +"*" { return '*'; } +"&" { return '&'; } + +([0][x][a-fA-F0-9]+) { + yylval.number = strtoul(yytext, NULL, 16); + return number; + } +([0][b][0-1]+) { + yylval.number = strtol(yytext + 2, NULL, 2); + return number; + } +(([0])|([-+]?[1-9][0-9]*)) { + yylval.number = strtol(yytext, NULL, 10); + return number; + } +([0][0-7]+) { + yylval.number = strtol(yytext + 1, NULL, 8); + return number; + } +[a-zA-Z_][a-zA-Z0-9_]+ { + yylval.label = strdup(yytext); + return label; + } + +"/*"([^\*]|\*[^/])*"*/" { /* NOP */ } +";"[^\n]* { /* NOP */ } +^#.* { /* NOP */ } +[ \t]+ { /* NOP */ } +[ \n]+ { /* NOP */ } + +. { + printf("unknown character \'%s\'", yytext); + yyerror("lex unknown character"); + } + +%% diff --git a/tools/bpf/bpf_exp.y b/tools/bpf/bpf_exp.y new file mode 100644 index 000000000..dfb7254a2 --- /dev/null +++ b/tools/bpf/bpf_exp.y @@ -0,0 +1,668 @@ +/* + * BPF asm code parser + * + * This program is free software; you can distribute it and/or modify + * it under the terms of the GNU General Public License as published + * by the Free Software Foundation; either version 2 of the License, + * or (at your option) any later version. + * + * Syntax kept close to: + * + * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new + * architecture for user-level packet capture. In Proceedings of the + * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993 + * Conference Proceedings (USENIX'93). USENIX Association, Berkeley, + * CA, USA, 2-2. + * + * Copyright 2013 Daniel Borkmann <borkmann@redhat.com> + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +%{ + +#include <stdio.h> +#include <string.h> +#include <stdint.h> +#include <stdlib.h> +#include <stdbool.h> +#include <unistd.h> +#include <errno.h> +#include <assert.h> +#include <linux/filter.h> + +#include "bpf_exp.yacc.h" + +enum jmp_type { JTL, JFL, JKL }; + +extern FILE *yyin; +extern int yylineno; +extern int yylex(void); +extern void yyerror(const char *str); + +extern void bpf_asm_compile(FILE *fp, bool cstyle); +static void bpf_set_curr_instr(uint16_t op, uint8_t jt, uint8_t jf, uint32_t k); +static void bpf_set_curr_label(char *label); +static void bpf_set_jmp_label(char *label, enum jmp_type type); + +%} + +%union { + char *label; + uint32_t number; +} + +%token OP_LDB OP_LDH OP_LD OP_LDX OP_ST OP_STX OP_JMP OP_JEQ OP_JGT OP_JGE +%token OP_JSET OP_ADD OP_SUB OP_MUL OP_DIV OP_AND OP_OR OP_XOR OP_LSH OP_RSH +%token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI +%token OP_LDXI + +%token K_PKT_LEN + +%token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%' + +%token extension number label + +%type <label> label +%type <number> extension +%type <number> number + +%% + +prog + : line + | prog line + ; + +line + : instr + | labelled_instr + ; + +labelled_instr + : labelled instr + ; + +instr + : ldb + | ldh + | ld + | ldi + | ldx + | ldxi + | st + | stx + | jmp + | jeq + | jneq + | jlt + | jle + | jgt + | jge + | jset + | add + | sub + | mul + | div + | mod + | neg + | and + | or + | xor + | lsh + | rsh + | ret + | tax + | txa + ; + +labelled + : label ':' { bpf_set_curr_label($1); } + ; + +ldb + : OP_LDB '[' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $5); } + | OP_LDB '[' '%' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); } + | OP_LDB '[' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); } + | OP_LDB extension { + bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, + SKF_AD_OFF + $2); } + ; + +ldh + : OP_LDH '[' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $5); } + | OP_LDH '[' '%' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); } + | OP_LDH '[' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); } + | OP_LDH extension { + bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, + SKF_AD_OFF + $2); } + ; + +ldi + : OP_LDI '#' number { + bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); } + | OP_LDI number { + bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $2); } + ; + +ld + : OP_LD '#' number { + bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); } + | OP_LD K_PKT_LEN { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); } + | OP_LD extension { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, + SKF_AD_OFF + $2); } + | OP_LD 'M' '[' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); } + | OP_LD '[' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $5); } + | OP_LD '[' '%' 'x' '+' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $6); } + | OP_LD '[' number ']' { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, $3); } + ; + +ldxi + : OP_LDXI '#' number { + bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); } + | OP_LDXI number { + bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $2); } + ; + +ldx + : OP_LDX '#' number { + bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); } + | OP_LDX K_PKT_LEN { + bpf_set_curr_instr(BPF_LDX | BPF_W | BPF_LEN, 0, 0, 0); } + | OP_LDX 'M' '[' number ']' { + bpf_set_curr_instr(BPF_LDX | BPF_MEM, 0, 0, $4); } + | OP_LDXB number '*' '(' '[' number ']' '&' number ')' { + if ($2 != 4 || $9 != 0xf) { + fprintf(stderr, "ldxb offset not supported!\n"); + 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(1); + } else { + bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } } + ; + +st + : OP_ST 'M' '[' number ']' { + bpf_set_curr_instr(BPF_ST, 0, 0, $4); } + ; + +stx + : OP_STX 'M' '[' number ']' { + bpf_set_curr_instr(BPF_STX, 0, 0, $4); } + ; + +jmp + : OP_JMP label { + bpf_set_jmp_label($2, JKL); + bpf_set_curr_instr(BPF_JMP | BPF_JA, 0, 0, 0); } + ; + +jeq + : OP_JEQ '#' number ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); } + | OP_JEQ 'x' ',' label ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_jmp_label($6, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + | OP_JEQ '%' 'x' ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + | OP_JEQ '#' number ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); } + | OP_JEQ 'x' ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + | OP_JEQ '%' 'x' ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + ; + +jneq + : OP_JNEQ '#' number ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); } + | OP_JNEQ 'x' ',' label { + bpf_set_jmp_label($4, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + | OP_JNEQ '%' 'x' ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); } + ; + +jlt + : OP_JLT '#' number ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); } + | OP_JLT 'x' ',' label { + bpf_set_jmp_label($4, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + | OP_JLT '%' 'x' ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + ; + +jle + : OP_JLE '#' number ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); } + | OP_JLE 'x' ',' label { + bpf_set_jmp_label($4, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + | OP_JLE '%' 'x' ',' label { + bpf_set_jmp_label($5, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + ; + +jgt + : OP_JGT '#' number ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); } + | OP_JGT 'x' ',' label ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_jmp_label($6, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + | OP_JGT '%' 'x' ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + | OP_JGT '#' number ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); } + | OP_JGT 'x' ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + | OP_JGT '%' 'x' ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); } + ; + +jge + : OP_JGE '#' number ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); } + | OP_JGE 'x' ',' label ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_jmp_label($6, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + | OP_JGE '%' 'x' ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + | OP_JGE '#' number ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); } + | OP_JGE 'x' ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + | OP_JGE '%' 'x' ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); } + ; + +jset + : OP_JSET '#' number ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); } + | OP_JSET 'x' ',' label ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_jmp_label($6, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); } + | OP_JSET '%' 'x' ',' label ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_jmp_label($7, JFL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); } + | OP_JSET '#' number ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); } + | OP_JSET 'x' ',' label { + bpf_set_jmp_label($4, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); } + | OP_JSET '%' 'x' ',' label { + bpf_set_jmp_label($5, JTL); + bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); } + ; + +add + : OP_ADD '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_K, 0, 0, $3); } + | OP_ADD 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); } + | OP_ADD '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); } + ; + +sub + : OP_SUB '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_K, 0, 0, $3); } + | OP_SUB 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); } + | OP_SUB '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); } + ; + +mul + : OP_MUL '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_K, 0, 0, $3); } + | OP_MUL 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); } + | OP_MUL '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); } + ; + +div + : OP_DIV '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_K, 0, 0, $3); } + | OP_DIV 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); } + | OP_DIV '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); } + ; + +mod + : OP_MOD '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_K, 0, 0, $3); } + | OP_MOD 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); } + | OP_MOD '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); } + ; + +neg + : OP_NEG { + bpf_set_curr_instr(BPF_ALU | BPF_NEG, 0, 0, 0); } + ; + +and + : OP_AND '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_K, 0, 0, $3); } + | OP_AND 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); } + | OP_AND '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); } + ; + +or + : OP_OR '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_K, 0, 0, $3); } + | OP_OR 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); } + | OP_OR '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); } + ; + +xor + : OP_XOR '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_K, 0, 0, $3); } + | OP_XOR 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); } + | OP_XOR '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); } + ; + +lsh + : OP_LSH '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_K, 0, 0, $3); } + | OP_LSH 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); } + | OP_LSH '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); } + ; + +rsh + : OP_RSH '#' number { + bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_K, 0, 0, $3); } + | OP_RSH 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); } + | OP_RSH '%' 'x' { + bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); } + ; + +ret + : OP_RET 'a' { + bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); } + | OP_RET '%' 'a' { + bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); } + | OP_RET 'x' { + bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); } + | OP_RET '%' 'x' { + bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); } + | OP_RET '#' number { + bpf_set_curr_instr(BPF_RET | BPF_K, 0, 0, $3); } + ; + +tax + : OP_TAX { + bpf_set_curr_instr(BPF_MISC | BPF_TAX, 0, 0, 0); } + ; + +txa + : OP_TXA { + bpf_set_curr_instr(BPF_MISC | BPF_TXA, 0, 0, 0); } + ; + +%% + +static int curr_instr = 0; +static struct sock_filter out[BPF_MAXINSNS]; +static char **labels, **labels_jt, **labels_jf, **labels_k; + +static void bpf_assert_max(void) +{ + if (curr_instr >= BPF_MAXINSNS) { + fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS); + exit(1); + } +} + +static void bpf_set_curr_instr(uint16_t code, uint8_t jt, uint8_t jf, + uint32_t k) +{ + bpf_assert_max(); + out[curr_instr].code = code; + out[curr_instr].jt = jt; + out[curr_instr].jf = jf; + out[curr_instr].k = k; + curr_instr++; +} + +static void bpf_set_curr_label(char *label) +{ + bpf_assert_max(); + labels[curr_instr] = label; +} + +static void bpf_set_jmp_label(char *label, enum jmp_type type) +{ + bpf_assert_max(); + switch (type) { + case JTL: + labels_jt[curr_instr] = label; + break; + case JFL: + labels_jf[curr_instr] = label; + break; + case JKL: + labels_k[curr_instr] = label; + break; + } +} + +static int bpf_find_insns_offset(const char *label) +{ + int i, max = curr_instr, ret = -ENOENT; + + for (i = 0; i < max; i++) { + if (labels[i] && !strcmp(label, labels[i])) { + ret = i; + break; + } + } + + if (ret == -ENOENT) { + fprintf(stderr, "no such label \'%s\'!\n", label); + exit(1); + } + + return ret; +} + +static void bpf_stage_1_insert_insns(void) +{ + yyparse(); +} + +static void bpf_reduce_k_jumps(void) +{ + int i; + + for (i = 0; i < curr_instr; i++) { + if (labels_k[i]) { + int off = bpf_find_insns_offset(labels_k[i]); + out[i].k = (uint32_t) (off - i - 1); + } + } +} + +static uint8_t bpf_encode_jt_jf_offset(int off, int i) +{ + int delta = off - i - 1; + + 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; +} + +static void bpf_reduce_jt_jumps(void) +{ + int i; + + for (i = 0; i < curr_instr; i++) { + if (labels_jt[i]) { + int off = bpf_find_insns_offset(labels_jt[i]); + out[i].jt = bpf_encode_jt_jf_offset(off, i); + } + } +} + +static void bpf_reduce_jf_jumps(void) +{ + int i; + + for (i = 0; i < curr_instr; i++) { + if (labels_jf[i]) { + int off = bpf_find_insns_offset(labels_jf[i]); + out[i].jf = bpf_encode_jt_jf_offset(off, i); + } + } +} + +static void bpf_stage_2_reduce_labels(void) +{ + bpf_reduce_k_jumps(); + bpf_reduce_jt_jumps(); + bpf_reduce_jf_jumps(); +} + +static void bpf_pretty_print_c(void) +{ + int i; + + for (i = 0; i < curr_instr; i++) + printf("{ %#04x, %2u, %2u, %#010x },\n", out[i].code, + out[i].jt, out[i].jf, out[i].k); +} + +static void bpf_pretty_print(void) +{ + int i; + + printf("%u,", curr_instr); + for (i = 0; i < curr_instr; i++) + printf("%u %u %u %u,", out[i].code, + out[i].jt, out[i].jf, out[i].k); + printf("\n"); +} + +static void bpf_init(void) +{ + memset(out, 0, sizeof(out)); + + labels = calloc(BPF_MAXINSNS, sizeof(*labels)); + assert(labels); + labels_jt = calloc(BPF_MAXINSNS, sizeof(*labels_jt)); + assert(labels_jt); + labels_jf = calloc(BPF_MAXINSNS, sizeof(*labels_jf)); + assert(labels_jf); + labels_k = calloc(BPF_MAXINSNS, sizeof(*labels_k)); + assert(labels_k); +} + +static void bpf_destroy_labels(void) +{ + int i; + + for (i = 0; i < curr_instr; i++) { + free(labels_jf[i]); + free(labels_jt[i]); + free(labels_k[i]); + free(labels[i]); + } +} + +static void bpf_destroy(void) +{ + bpf_destroy_labels(); + free(labels_jt); + free(labels_jf); + free(labels_k); + free(labels); +} + +void bpf_asm_compile(FILE *fp, bool cstyle) +{ + yyin = fp; + + bpf_init(); + bpf_stage_1_insert_insns(); + bpf_stage_2_reduce_labels(); + bpf_destroy(); + + if (cstyle) + bpf_pretty_print_c(); + else + bpf_pretty_print(); + + if (fp != stdin) + fclose(yyin); +} + +void yyerror(const char *str) +{ + fprintf(stderr, "error: %s at line %d\n", str, yylineno); + exit(1); +} diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c new file mode 100644 index 000000000..5ab8f80e2 --- /dev/null +++ b/tools/bpf/bpf_jit_disasm.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Minimal BPF JIT image disassembler + * + * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for + * debugging or verification purposes. + * + * To get the disassembly of the JIT code, do the following: + * + * 1) `echo 2 > /proc/sys/net/core/bpf_jit_enable` + * 2) Load a BPF filter (e.g. `tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24`) + * 3) Run e.g. `bpf_jit_disasm -o` to read out the last JIT code + * + * Copyright 2013 Daniel Borkmann <borkmann@redhat.com> + */ + +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <assert.h> +#include <unistd.h> +#include <string.h> +#include <bfd.h> +#include <dis-asm.h> +#include <regex.h> +#include <fcntl.h> +#include <sys/klog.h> +#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 + +static void get_exec_path(char *tpath, size_t size) +{ + char *path; + ssize_t len; + + snprintf(tpath, size, "/proc/%d/exe", (int) getpid()); + tpath[size - 1] = 0; + + path = strdup(tpath); + assert(path); + + len = readlink(path, tpath, size); + if (len < 0) + len = 0; + tpath[len] = 0; + + free(path); +} + +static void get_asm_insns(uint8_t *image, size_t len, int opcodes) +{ + int count, i, pc = 0; + char tpath[PATH_MAX]; + struct disassemble_info info; + disassembler_ftype disassemble; + bfd *bfdf; + + memset(tpath, 0, sizeof(tpath)); + get_exec_path(tpath, sizeof(tpath)); + + bfdf = bfd_openr(tpath, NULL); + assert(bfdf); + assert(bfd_check_format(bfdf, bfd_object)); + + 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; + info.buffer_length = len; + + disassemble_init_for_target(&info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + disassemble = disassembler(info.arch, + bfd_big_endian(bfdf), + info.mach, + bfdf); +#else + disassemble = disassembler(bfdf); +#endif + assert(disassemble); + + do { + printf("%4x:\t", pc); + + count = disassemble(pc, &info); + + if (opcodes) { + printf("\n\t"); + for (i = 0; i < count; ++i) + printf("%02x ", (uint8_t) image[pc + i]); + } + printf("\n"); + + pc += count; + } while(count > 0 && pc < len); + + bfd_close(bfdf); +} + +static char *get_klog_buff(unsigned int *klen) +{ + int ret, len; + char *buff; + + len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0); + if (len < 0) + return NULL; + + buff = malloc(len); + if (!buff) + return NULL; + + ret = klogctl(CMD_ACTION_READ_ALL, buff, len); + if (ret < 0) { + free(buff); + return NULL; + } + + *klen = ret; + return buff; +} + +static char *get_flog_buff(const char *file, unsigned int *klen) +{ + int fd, ret, len; + struct stat fi; + char *buff; + + fd = open(file, O_RDONLY); + if (fd < 0) + return NULL; + + ret = fstat(fd, &fi); + if (ret < 0 || !S_ISREG(fi.st_mode)) + goto out; + + len = fi.st_size + 1; + buff = malloc(len); + if (!buff) + goto out; + + memset(buff, 0, len); + ret = read(fd, buff, len - 1); + if (ret <= 0) + goto out_free; + + close(fd); + *klen = ret; + return buff; +out_free: + free(buff); +out: + close(fd); + return NULL; +} + +static char *get_log_buff(const char *file, unsigned int *klen) +{ + return file ? get_flog_buff(file, klen) : get_klog_buff(klen); +} + +static void put_log_buff(char *buff) +{ + free(buff); +} + +static uint8_t *get_last_jit_image(char *haystack, size_t hlen, + unsigned int *ilen) +{ + char *ptr, *pptr, *tmp; + off_t off = 0; + unsigned int proglen; + int ret, flen, pass, ulen = 0; + regmatch_t pmatch[1]; + unsigned long base; + regex_t regex; + uint8_t *image; + + if (hlen == 0) + return NULL; + + ret = regcomp(®ex, "flen=[[:alnum:]]+ proglen=[[:digit:]]+ " + "pass=[[:digit:]]+ image=[[:xdigit:]]+", REG_EXTENDED); + assert(ret == 0); + + ptr = haystack; + memset(pmatch, 0, sizeof(pmatch)); + + while (1) { + ret = regexec(®ex, ptr, 1, pmatch, 0); + if (ret == 0) { + ptr += pmatch[0].rm_eo; + off += pmatch[0].rm_eo; + assert(off < hlen); + } else + break; + } + + ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so); + ret = sscanf(ptr, "flen=%d proglen=%u pass=%d image=%lx", + &flen, &proglen, &pass, &base); + if (ret != 4) { + regfree(®ex); + return NULL; + } + if (proglen > 1000000) { + printf("proglen of %u too big, stopping\n", proglen); + return NULL; + } + + image = malloc(proglen); + if (!image) { + printf("Out of memory\n"); + return NULL; + } + memset(image, 0, proglen); + + tmp = ptr = haystack + off; + while ((ptr = strtok(tmp, "\n")) != NULL && ulen < proglen) { + tmp = NULL; + if (!strstr(ptr, "JIT code")) + continue; + pptr = ptr; + while ((ptr = strstr(pptr, ":"))) + pptr = ptr + 1; + ptr = pptr; + do { + image[ulen++] = (uint8_t) strtoul(pptr, &pptr, 16); + if (ptr == pptr) { + ulen--; + break; + } + if (ulen >= proglen) + break; + ptr = pptr; + } while (1); + } + + assert(ulen == proglen); + printf("%u bytes emitted from JIT compiler (pass:%d, flen:%d)\n", + proglen, pass, flen); + printf("%lx + <x>:\n", base); + + regfree(®ex); + *ilen = ulen; + return image; +} + +static void usage(void) +{ + printf("Usage: bpf_jit_disasm [...]\n"); + printf(" -o Also display related opcodes (default: off).\n"); + printf(" -O <file> Write binary image of code to file, don't disassemble to stdout.\n"); + printf(" -f <file> Read last image dump from file or stdin (default: klog).\n"); + printf(" -h Display this help.\n"); +} + +int main(int argc, char **argv) +{ + unsigned int len, klen, opt, opcodes = 0; + char *kbuff, *file = NULL; + char *ofile = NULL; + int ofd; + ssize_t nr; + uint8_t *pos; + uint8_t *image = NULL; + + while ((opt = getopt(argc, argv, "of:O:")) != -1) { + switch (opt) { + case 'o': + opcodes = 1; + break; + case 'O': + ofile = optarg; + break; + case 'f': + file = optarg; + break; + default: + usage(); + return -1; + } + } + + bfd_init(); + + kbuff = get_log_buff(file, &klen); + if (!kbuff) { + fprintf(stderr, "Could not retrieve log buffer!\n"); + return -1; + } + + image = get_last_jit_image(kbuff, klen, &len); + if (!image) { + fprintf(stderr, "No JIT image found!\n"); + goto done; + } + if (!ofile) { + get_asm_insns(image, len, opcodes); + goto done; + } + + ofd = open(ofile, O_WRONLY | O_CREAT | O_TRUNC, DEFFILEMODE); + if (ofd < 0) { + fprintf(stderr, "Could not open file %s for writing: ", ofile); + perror(NULL); + goto done; + } + pos = image; + do { + nr = write(ofd, pos, len); + if (nr < 0) { + fprintf(stderr, "Could not write data to %s: ", ofile); + perror(NULL); + goto done; + } + len -= nr; + pos += nr; + } while (len); + close(ofd); + +done: + put_log_buff(kbuff); + free(image); + return 0; +} diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore new file mode 100644 index 000000000..a736f64dc --- /dev/null +++ b/tools/bpf/bpftool/.gitignore @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +*.d +/bootstrap/ +/bpftool +bpftool*.8 +FEATURE-DUMP.bpftool +feature +libbpf +/*.skel.h +/vmlinux.h diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile new file mode 100644 index 000000000..bf843f328 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +include ../../../scripts/Makefile.include + +INSTALL ?= install +RM ?= rm -f +RMDIR ?= rmdir --ignore-fail-on-non-empty + +prefix ?= /usr/local +mandir ?= $(prefix)/man +man8dir = $(mandir)/man8 + +MAN8_RST = $(wildcard bpftool*.rst) + +_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) +DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) + +man: man8 +man8: $(DOC_MAN8) + +RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) +RST2MAN_OPTS += --verbose --strip-comments + +list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST)))) +see_also = $(subst " ",, \ + "\n" \ + "SEE ALSO\n" \ + "========\n" \ + "**bpf**\ (2),\n" \ + "**bpf-helpers**\\ (7)" \ + $(foreach page,$(call list_pages,$(1)),",\n**$(page)**\\ (8)") \ + "\n") + +$(OUTPUT)%.8: %.rst +ifndef RST2MAN_DEP + $(error "rst2man not found, but required to generate man pages") +endif + $(QUIET_GEN)( cat $< ; printf "%b" $(call see_also,$<) ) | rst2man $(RST2MAN_OPTS) > $@ + +clean: + $(call QUIET_CLEAN, Documentation) + $(Q)$(RM) $(DOC_MAN8) + +install: man + $(call QUIET_INSTALL, Documentation-man) + $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir) + $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir) + +uninstall: + $(call QUIET_UNINST, Documentation-man) + $(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8)) + $(Q)$(RMDIR) $(DESTDIR)$(man8dir) + +.PHONY: man man8 clean install uninstall +.DEFAULT_GOAL := man diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000..cf75a7fa2 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,272 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **btf** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } } + +*COMMANDS* := { **dump** | **help** } + +BTF COMMANDS +============= + +| **bpftool** **btf** { **show** | **list** } [**id** *BTF_ID*] +| **bpftool** **btf dump** *BTF_SRC* [**format** *FORMAT*] [**root_id** *ROOT_ID*] +| **bpftool** **btf help** +| +| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* [**file** *FILE*]... } +| *FORMAT* := { **raw** | **c** [**unsorted**] } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } + +DESCRIPTION +=========== +bpftool btf { show | list } [id *BTF_ID*] + Show information about loaded BTF objects. If a BTF ID is specified, show + information only about given BTF object, otherwise list all BTF objects + currently loaded on the system. + + Since Linux 5.8 bpftool is able to discover information about processes + that hold open file descriptors (FDs) against BTF objects. On such kernels + bpftool will automatically emit this information as well. + +bpftool btf dump *BTF_SRC* [format *FORMAT*] [root_id *ROOT_ID*] + Dump BTF entries from a given *BTF_SRC*. + + When **id** is specified, BTF object with that ID will be loaded and all + its BTF types emitted. + + When **map** is provided, it's expected that map has associated BTF object + with BTF types describing key and value. It's possible to select whether to + dump only BTF type(s) associated with key (**key**), value (**value**), + both key and value (**kv**), or all BTF types present in associated BTF + object (**all**). If not specified, **kv** is assumed. + + When **prog** is provided, it's expected that program has associated BTF + object with BTF types. + + When specifying *FILE*, an ELF file or a raw BTF file (e.g. from + ``/sys/kernel/btf/``) is expected. Multiple **file** arguments may be + given to merge BTF from several kernel modules into a single output. + When sysfs paths are used, vmlinux BTF is loaded automatically as the + base; if vmlinux itself appears in the file list it is skipped. + A base BTF can also be specified explicitly with **-B**. + + **format** option can be used to override default (raw) output format. Raw + (**raw**) or C-syntax (**c**) output formats are supported. With C-style + formatting, the output is sorted by default. Use the **unsorted** option + to avoid sorting the output. + + **root_id** option can be used to filter a dump to a single type and all + its dependent types. It cannot be used with any other types of filtering + (such as the "key", "value", or "kv" arguments when dumping BTF for a map). + It can be passed multiple times to dump multiple types. + +bpftool btf help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +-B, --base-btf *FILE* + Pass a base BTF object. Base BTF objects are typically used with BTF + objects for kernel modules. To avoid duplicating all kernel symbols + required by modules, BTF objects for modules are "split", they are + built incrementally on top of the kernel (vmlinux) BTF object. So the + base BTF reference should usually point to the kernel BTF. + + When the main BTF object to process (for example, the module BTF to + dump) is passed as a *FILE*, bpftool attempts to autodetect the path + for the base object, and passing this option is optional. When the main + BTF object is passed through other handles, this option becomes + necessary. + +EXAMPLES +======== +**# bpftool btf dump id 1226** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2 + 'pad' type_id=3 bits_offset=0 + 'sock' type_id=4 bits_offset=64 + [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [4] PTR '(anon)' type_id=5 + [5] FWD 'sock' fwd_kind=union + +This gives an example of default output for all supported BTF kinds. + +**$ cat prog.c** + +:: + + struct fwd_struct; + + enum my_enum { + VAL1 = 3, + VAL2 = 7, + }; + + typedef struct my_struct my_struct_t; + + struct my_struct { + const unsigned int const_int_field; + int bitfield_field: 4; + char arr_field[16]; + const struct fwd_struct *restrict fwd_field; + enum my_enum enum_field; + volatile my_struct_t *typedef_ptr_field; + }; + + union my_union { + int a; + struct my_struct b; + }; + + struct my_struct struct_global_var __attribute__((section("data_sec"))) = { + .bitfield_field = 3, + .enum_field = VAL1, + }; + int global_var __attribute__((section("data_sec"))) = 7; + + __attribute__((noinline)) + int my_func(union my_union *arg1, int arg2) + { + static int static_var __attribute__((section("data_sec"))) = 123; + static_var++; + return static_var; + } + +**$ bpftool btf dump file prog.o** + +:: + + [1] PTR '(anon)' type_id=2 + [2] UNION 'my_union' size=48 vlen=2 + 'a' type_id=3 bits_offset=0 + 'b' type_id=4 bits_offset=0 + [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + [4] STRUCT 'my_struct' size=48 vlen=6 + 'const_int_field' type_id=5 bits_offset=0 + 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4 + 'arr_field' type_id=8 bits_offset=40 + 'fwd_field' type_id=10 bits_offset=192 + 'enum_field' type_id=14 bits_offset=256 + 'typedef_ptr_field' type_id=15 bits_offset=320 + [5] CONST '(anon)' type_id=6 + [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED + [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16 + [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [10] RESTRICT '(anon)' type_id=11 + [11] PTR '(anon)' type_id=12 + [12] CONST '(anon)' type_id=13 + [13] FWD 'fwd_struct' fwd_kind=union + [14] ENUM 'my_enum' size=4 vlen=2 + 'VAL1' val=3 + 'VAL2' val=7 + [15] PTR '(anon)' type_id=16 + [16] VOLATILE '(anon)' type_id=17 + [17] TYPEDEF 'my_struct_t' type_id=4 + [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2 + 'arg1' type_id=1 + 'arg2' type_id=3 + [19] FUNC 'my_func' type_id=18 + [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc + [21] VAR 'global_var' type_id=3, linkage=global-alloc + [22] VAR 'my_func.static_var' type_id=3, linkage=static + [23] DATASEC 'data_sec' size=0 vlen=3 + type_id=20 offset=0 size=48 + type_id=21 offset=0 size=4 + type_id=22 offset=52 size=4 + +The following commands print BTF types associated with specified map's key, +value, both key and value, and all BTF types, respectively. By default, both +key and value types will be printed. + +**# bpftool btf dump map id 123 key** + +:: + + [39] TYPEDEF 'u32' type_id=37 + +**# bpftool btf dump map id 123 value** + +:: + + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 kv** + +:: + + [39] TYPEDEF 'u32' type_id=37 + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 all** + +:: + + [1] PTR '(anon)' type_id=0 + . + . + . + [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4 + +All the standard ways to specify map or program are supported: + +**# bpftool btf dump map id 123** + +**# bpftool btf dump map pinned /sys/fs/bpf/map_name** + +**# bpftool btf dump prog id 456** + +**# bpftool btf dump prog tag b88e0a09b1d9759d** + +**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** + +| +| **# bpftool btf dump file /sys/kernel/btf/i2c_smbus** +| (or) +| **# I2C_SMBUS_ID=$(bpftool btf show -p | jq '.[] | select(.name=="i2c_smbus").id')** +| **# bpftool btf dump id ${I2C_SMBUS_ID} -B /sys/kernel/btf/vmlinux** + +:: + + [104848] STRUCT 'i2c_smbus_alert' size=40 vlen=2 + 'alert' type_id=393 bits_offset=0 + 'ara' type_id=56050 bits_offset=256 + [104849] STRUCT 'alert_data' size=12 vlen=3 + 'addr' type_id=16 bits_offset=0 + 'type' type_id=56053 bits_offset=32 + 'data' type_id=7 bits_offset=64 + [104850] PTR '(anon)' type_id=104848 + [104851] PTR '(anon)' type_id=104849 + [104852] FUNC 'i2c_register_spd' type_id=84745 linkage=static + [104853] FUNC 'smbalert_driver_init' type_id=1213 linkage=static + [104854] FUNC_PROTO '(anon)' ret_type_id=18 vlen=1 + 'ara' type_id=56050 + [104855] FUNC 'i2c_handle_smbus_alert' type_id=104854 linkage=static + [104856] FUNC 'smbalert_remove' type_id=104854 linkage=static + [104857] FUNC_PROTO '(anon)' ret_type_id=18 vlen=2 + 'ara' type_id=56050 + 'id' type_id=56056 + [104858] FUNC 'smbalert_probe' type_id=104857 linkage=static + [104859] FUNC 'smbalert_work' type_id=9695 linkage=static + [104860] FUNC 'smbus_alert' type_id=71367 linkage=static + [104861] FUNC 'smbus_do_alert' type_id=84827 linkage=static diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst new file mode 100644 index 000000000..e8185596a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -0,0 +1,158 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-cgroup +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF progs +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **cgroup** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } } + +*COMMANDS* := +{ **show** | **list** | **tree** | **attach** | **detach** | **help** } + +CGROUP COMMANDS +=============== + +| **bpftool** **cgroup** { **show** | **list** } *CGROUP* [**effective**] +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] +| **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] +| **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* +| **bpftool** **cgroup help** +| +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *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 +=========== +bpftool cgroup { show | list } *CGROUP* [effective] + List all programs attached to the cgroup *CGROUP*. + + Output will start with program ID followed by attach type, attach flags and + program name. + + If **effective** is specified retrieve effective programs that will execute + for events within a cgroup. This includes inherited along with attached + ones. + +bpftool cgroup tree [*CGROUP_ROOT*] [effective] + Iterate over all cgroups in *CGROUP_ROOT* and list all attached programs. + If *CGROUP_ROOT* is not specified, bpftool uses cgroup v2 mountpoint. + + The output is similar to the output of cgroup show/list commands: it starts + with absolute cgroup path, followed by program ID, attach type, attach + flags and program name. + + If **effective** is specified retrieve effective programs that will execute + for events within a cgroup. This includes inherited along with attached + ones. + +bpftool cgroup attach *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] + Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* + and optional *ATTACH_FLAGS*. + + *ATTACH_FLAGS* can be one of: **override** if a sub-cgroup installs some + bpf program, the program in this cgroup yields to sub-cgroup program; + **multi** if a sub-cgroup installs some bpf program, that cgroup program + gets run in addition to the program in this cgroup. + + Only one program is allowed to be attached to a cgroup with no attach flags + or the **override** flag. Attaching another program will release old + program and attach the new one. + + Multiple programs are allowed to be attached to a cgroup with **multi**. + They are executed in FIFO order (those that were attached first, run + first). + + Non-default *ATTACH_FLAGS* are supported by kernel version 4.14 and later. + + *ATTACH_TYPE* can be one of: + + - **ingress** ingress path of the inet socket (since 4.10) + - **egress** egress path of the inet socket (since 4.10) + - **sock_create** opening of an inet socket (since 4.10) + - **sock_ops** various socket operations (since 4.12) + - **device** device access (since 4.15) + - **bind4** call to bind(2) for an inet4 socket (since 4.17) + - **bind6** call to bind(2) for an inet6 socket (since 4.17) + - **post_bind4** return from bind(2) for an inet4 socket (since 4.17) + - **post_bind6** return from bind(2) for an inet6 socket (since 4.17) + - **connect4** call to connect(2) for an inet4 socket (since 4.17) + - **connect6** call to connect(2) for an inet6 socket (since 4.17) + - **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) + - **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for 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 a userspace inet socket (since 5.9) + +bpftool cgroup detach *CGROUP* *ATTACH_TYPE* *PROG* + Detach *PROG* from the cgroup *CGROUP* and attach type *ATTACH_TYPE*. + +bpftool prog help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +-f, --bpffs + Show file names of pinned programs. + +EXAMPLES +======== +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# mkdir /sys/fs/cgroup/test.slice** +| **# bpftool prog load ./device_cgroup.o /sys/fs/bpf/prog** +| **# bpftool cgroup attach /sys/fs/cgroup/test.slice/ device id 1 allow_multi** + +**# bpftool cgroup list /sys/fs/cgroup/test.slice/** + +:: + + ID AttachType AttachFlags Name + 1 device allow_multi bpf_prog1 + +| +| **# bpftool cgroup detach /sys/fs/cgroup/test.slice/ device id 1** +| **# bpftool cgroup list /sys/fs/cgroup/test.slice/** + +:: + + ID AttachType AttachFlags Name diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst new file mode 100644 index 000000000..c7f837898 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -0,0 +1,83 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +=============== +bpftool-feature +=============== +------------------------------------------------------------------------------- +tool for inspection of eBPF-related parameters for Linux kernel or net device +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **feature** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := { **probe** | **help** } + +FEATURE COMMANDS +================ + +| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature list_builtins** *GROUP* +| **bpftool** **feature help** +| +| *COMPONENT* := { **kernel** | **dev** *NAME* } +| *GROUP* := { **prog_types** | **map_types** | **attach_types** | **link_types** | **helpers** } + +DESCRIPTION +=========== +bpftool feature probe [kernel] [full] [macros [prefix *PREFIX*]] + Probe the running kernel and dump a number of eBPF-related parameters, such + as availability of the **bpf**\ () system call, JIT status, eBPF program + types availability, eBPF helper functions availability, and more. + + By default, bpftool **does not run probes** for **bpf_probe_write_user**\ + () and **bpf_trace_printk**\() helpers which print warnings to kernel logs. + To enable them and run all probes, the **full** keyword should be used. + + If the **macros** keyword (but not the **-j** option) is passed, a subset + of the output is dumped as a list of **#define** macros that are ready to + be included in a C header file, for example. If, additionally, **prefix** + is used to define a *PREFIX*, the provided string will be used as a prefix + to the names of the macros: this can be used to avoid conflicts on macro + names when including the output of this command as a header file. + + Keyword **kernel** can be omitted. If no probe target is specified, probing + the kernel is the default behaviour. + + When the **unprivileged** keyword is used, bpftool will dump only the + features available to a user who does not have the **CAP_SYS_ADMIN** + capability set. The features available in that case usually represent a + small subset of the parameters supported by the system. Unprivileged users + MUST use the **unprivileged** keyword: This is to avoid misdetection if + bpftool is inadvertently run as non-root, for example. This keyword is + unavailable if bpftool was compiled without libcap. + +bpftool feature probe dev *NAME* [full] [macros [prefix *PREFIX*]] + Probe network device for supported eBPF features and dump results to the + console. + + The keywords **full**, **macros** and **prefix** have the same role as when + probing the kernel. + +bpftool feature list_builtins *GROUP* + List items known to bpftool. These can be BPF program types + (**prog_types**), BPF map types (**map_types**), attach types + (**attach_types**), link types (**link_types**), or BPF helper functions + (**helpers**). The command does not probe the system, but simply lists the + elements that bpftool knows from compilation time, as provided from libbpf + (for all object types) or from the BPF UAPI header (list of helpers). This + can be used in scripts to iterate over BPF types or helpers. + +bpftool feature help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000..d0a36f442 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,481 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **gen** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } | [ { **-S** | **--sign** } {**-k** <private_key.pem>} **-i** <certificate.x509> ] } + +*COMMAND* := { **object** | **skeleton** | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] +| **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] +| **bpftool** **gen help** + +DESCRIPTION +=========== +bpftool gen object *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] + Statically link (combine) together one or more *INPUT_FILE*'s into a single + resulting *OUTPUT_FILE*. All the files involved are BPF ELF object files. + + The rules of BPF static linking are mostly the same as for user-space + object files, but in addition to combining data and instruction sections, + .BTF and .BTF.ext (if present in any of the input files) data are combined + together. .BTF data is deduplicated, so all the common types across + *INPUT_FILE*'s will only be represented once in the resulting BTF + information. + + BPF static linking allows to partition BPF source code into individually + compiled files that are then linked into a single resulting BPF object + file, which can be used to generated BPF skeleton (with **gen skeleton** + command) or passed directly into **libbpf** (using **bpf_object__open()** + family of APIs). + +bpftool gen skeleton *FILE* + Generate BPF skeleton C header file for a given *FILE*. + + BPF skeleton is an alternative interface to existing libbpf APIs for + working with BPF objects. Skeleton code is intended to significantly + shorten and simplify code to load and work with BPF programs from userspace + side. Generated code is tailored to specific input BPF object *FILE*, + reflecting its structure by listing out available maps, program, variables, + etc. Skeleton eliminates the need to lookup mentioned components by name. + Instead, if skeleton instantiation succeeds, they are populated in skeleton + structure as valid libbpf types (e.g., **struct bpf_map** pointer) and can + be passed to existing generic libbpf APIs. + + In addition to simple and reliable access to maps and programs, skeleton + provides a storage for BPF links (**struct bpf_link**) for each BPF program + within BPF object. When requested, supported BPF programs will be + automatically attached and resulting BPF links stored for further use by + user in pre-allocated fields in skeleton struct. For BPF programs that + can't be automatically attached by libbpf, user can attach them manually, + but store resulting BPF link in per-program link field. All such set up + links will be automatically destroyed on BPF skeleton destruction. This + eliminates the need for users to manage links manually and rely on libbpf + support to detach programs and free up resources. + + Another facility provided by BPF skeleton is an interface to global + variables of all supported kinds: mutable, read-only, as well as extern + ones. This interface allows to pre-setup initial values of variables before + BPF object is loaded and verified by kernel. For non-read-only variables, + the same interface can be used to fetch values of global variables on + userspace side, even if they are modified by BPF code. + + During skeleton generation, contents of source BPF object *FILE* is + embedded within generated code and is thus not necessary to keep around. + This ensures skeleton and BPF object file are matching 1-to-1 and always + stay in sync. Generated code is dual-licensed under LGPL-2.1 and + BSD-2-Clause licenses. + + It is a design goal and guarantee that skeleton interfaces are + interoperable with generic libbpf APIs. User should always be able to use + skeleton API to create and load BPF object, and later use libbpf APIs to + keep working with specific maps, programs, etc. + + As part of skeleton, few custom functions are generated. Each of them is + prefixed with object name. Object name can either be derived from object + file name, i.e., if BPF object file name is **example.o**, BPF object name + will be **example**. Object name can be also specified explicitly through + **name** *OBJECT_NAME* parameter. The following custom functions are + provided (assuming **example** as the object name): + + - **example__open** and **example__open_opts**. + These functions are used to instantiate skeleton. It corresponds to + libbpf's **bpf_object__open**\ () API. **_opts** variants accepts extra + **bpf_object_open_opts** options. + + - **example__load**. + This function creates maps, loads and verifies BPF programs, initializes + global data maps. It corresponds to libbpf's **bpf_object__load**\ () + API. + + - **example__open_and_load** combines **example__open** and + **example__load** invocations in one commonly used operation. + + - **example__attach** and **example__detach**. + This pair of functions allow to attach and detach, correspondingly, + already loaded BPF object. Only BPF programs of types supported by libbpf + for auto-attachment will be auto-attached and their corresponding BPF + links instantiated. For other BPF programs, user can manually create a + BPF link and assign it to corresponding fields in skeleton struct. + **example__detach** will detach both links created automatically, as well + as those populated by user manually. + + - **example__destroy**. + Detach and unload BPF programs, free up all the resources used by + skeleton and BPF object. + + If BPF object has global variables, corresponding structs with memory + layout corresponding to global data data section layout will be created. + Currently supported ones are: *.data*, *.bss*, *.rodata*, and *.kconfig* + structs/data sections. These data sections/structs can be used to set up + initial values of variables, if set before **example__load**. Afterwards, + if target kernel supports memory-mapped BPF arrays, same structs can be + used to fetch and update (non-read-only) data from userspace, with same + simplicity as for BPF side. + +bpftool gen subskeleton *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own the + corresponding maps, programs, or global variables. They require that the + object file used to generate them is already loaded into a *bpf_object* by + some other means. + + This functionality is useful when a library is included into a larger BPF + program. A subskeleton for the library would have access to all objects and + globals defined in it, without having to know about the larger program. + + Consequently, there are only two functions defined for subskeletons: + + - **example__open(bpf_object\*)**. + Instantiates a subskeleton from an already opened (but not necessarily + loaded) **bpf_object**. + + - **example__destroy()**. + Frees the storage for the subskeleton but *does not* unload any BPF + programs or maps. + +bpftool gen min_core_btf *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given *INPUT* BTF + file, containing all needed BTF types so one, or more, given eBPF objects + CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, libbpf, when + loading an eBPF object, has to rely on external BTF files to be able to + calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel DWARF data + using pahole. It contains all the types used by its respective kernel image + and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized to one or + multiple eBPF objects, so they can be distributed together with an eBPF + CO-RE based application, turning the application portable to different + kernel versions. + + Check examples below for more information on how to use it. + +bpftool gen help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +-L, --use-loader + For skeletons, generate a "light" skeleton (also known as "loader" + skeleton). A light skeleton contains a loader eBPF program. It does not use + the majority of the libbpf infrastructure, and does not need libelf. + +-S, --sign + For skeletons, generate a signed skeleton. This option must be used with + **-k** and **-i**. Using this flag implicitly enables **--use-loader**. + +-k <private_key.pem> + Path to the private key file in PEM format, required for signing. + +-i <certificate.x509> + Path to the X.509 certificate file in PEM or DER format, required for + signing. + +EXAMPLES +======== +**$ cat example1.bpf.c** + +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + SEC("raw_tp/sys_enter") + int handle_sys_enter(struct pt_regs *ctx) + { + static long my_static_var; + if (global_flag) + my_static_var++; + else + data.x += param1; + return 0; + } + +**$ cat example2.bpf.c** + +:: + + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + + SEC("raw_tp/sys_exit") + int handle_sys_exit(struct pt_regs *ctx) + { + int zero = 0; + bpf_map_lookup_elem(&my_map, &zero); + return 0; + } + +**$ 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** + +:: + + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + + /* THIS FILE IS AUTOGENERATED! */ + #ifndef __EXAMPLE_SKEL_H__ + #define __EXAMPLE_SKEL_H__ + + #include <stdlib.h> + #include <bpf/libbpf.h> + + struct example { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + struct bpf_map *data; + struct bpf_map *bss; + struct bpf_map *my_map; + 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; + } progs; + struct { + struct bpf_link *handle_sys_enter; + struct bpf_link *handle_sys_exit; + } links; + struct example__bss { + struct { + int x; + } data; + int test_2_result; + } *bss; + struct example__data { + _Bool global_flag; + long int handle_sys_enter_my_static_var; + } *data; + struct example__rodata { + int param1; + } *rodata; + }; + + static void example__destroy(struct example *obj); + static inline struct example *example__open_opts( + const struct bpf_object_open_opts *opts); + static inline struct example *example__open(); + static inline int example__load(struct example *obj); + static inline struct example *example__open_and_load(); + static inline int example__attach(struct example *obj); + static inline void example__detach(struct example *obj); + + #endif /* __EXAMPLE_SKEL_H__ */ + +**$ cat example.c** + +:: + + #include "example.skel.h" + + int main() + { + struct example *skel; + int err = 0; + + skel = example__open(); + if (!skel) + goto cleanup; + + skel->rodata->param1 = 128; + + /* 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; + + /* all libbpf APIs are usable */ + printf("my_map name: %s\n", bpf_map__name(skel->maps.my_map)); + printf("sys_enter prog FD: %d\n", + bpf_program__fd(skel->progs.handle_sys_enter)); + + /* detach and re-attach sys_exit program */ + bpf_link__destroy(skel->links.handle_sys_exit); + skel->links.handle_sys_exit = + bpf_program__attach(skel->progs.handle_sys_exit); + + printf("my_static_var: %ld\n", + skel->bss->handle_sys_enter_my_static_var); + + cleanup: + example__destroy(skel); + return err; + } + +**# ./example** + +:: + + 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. + +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst new file mode 100644 index 000000000..2e5d81c90 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -0,0 +1,72 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +============ +bpftool-iter +============ +------------------------------------------------------------------------------- +tool to create BPF iterators +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **iter** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := { **pin** | **help** } + +ITER COMMANDS +============= + +| **bpftool** **iter pin** *OBJ* *PATH* [**map** *MAP*] +| **bpftool** **iter help** +| +| *OBJ* := /a/file/of/bpf_iter_target.o +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } + +DESCRIPTION +=========== +bpftool iter pin *OBJ* *PATH* [map *MAP*] + A bpf iterator combines a kernel iterating of particular kernel data (e.g., + tasks, bpf_maps, etc.) and a bpf program called for each kernel data object + (e.g., one task, one bpf_map, etc.). User space can *read* kernel iterator + output through *read()* syscall. + + The *pin* command creates a bpf iterator from *OBJ*, and pin it to *PATH*. + The *PATH* should be located in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions of *bpffs*. + + Map element bpf iterator requires an additional parameter *MAP* so bpf + program can iterate over map elements for that map. User can have a bpf + program in kernel to run with each map element, do checking, filtering, + aggregation, etc. without copying data to user space. + + User can then *cat PATH* to see the bpf iterator output. + +bpftool iter help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +EXAMPLES +======== +**# bpftool iter pin bpf_iter_netlink.o /sys/fs/bpf/my_netlink** + +:: + + Create a file-based bpf iterator from bpf_iter_netlink.o and pin it + to /sys/fs/bpf/my_netlink + +**# bpftool iter pin bpf_iter_hashmap.o /sys/fs/bpf/my_hashmap map id 20** + +:: + + Create a file-based bpf iterator from bpf_iter_hashmap.o and map with + id 20, and pin it to /sys/fs/bpf/my_hashmap diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst new file mode 100644 index 000000000..6f09d4405 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -0,0 +1,107 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-link +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF links +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **link** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + +*COMMANDS* := { **show** | **list** | **pin** | **help** } + +LINK COMMANDS +============= + +| **bpftool** **link { show | list }** [*LINK*] +| **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link detach** *LINK* +| **bpftool** **link help** +| +| *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } + + +DESCRIPTION +=========== +bpftool link { show | list } [*LINK*] + Show information about active links. If *LINK* is specified show + information only about given link, otherwise list all links currently + active on the system. + + Output will start with link ID followed by link type and zero or more named + attributes, some of which depend on type of link. + + Since Linux 5.8 bpftool is able to discover information about processes + that hold open file descriptors (FDs) against BPF links. On such kernels + bpftool will automatically emit this information as well. + +bpftool link pin *LINK* *FILE* + Pin link *LINK* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions of *bpffs*. + +bpftool link detach *LINK* + Force-detach link *LINK*. BPF link and its underlying BPF program will stay + valid, but they will be detached from the respective BPF hook and BPF link + will transition into a defunct state until last open file descriptor for + that link is closed. + +bpftool link help + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + + -f, --bpffs + When showing BPF links, show file names of pinned links. + + -n, --nomount + Do not automatically attempt to mount any virtual file system (such as + tracefs or BPF virtual file system) when necessary. + +EXAMPLES +======== +**# bpftool link show** + +:: + + 10: cgroup prog 25 + cgroup_id 614 attach_type egress + pids test_progs(223) + +**# bpftool --json --pretty link show** + +:: + + [{ + "type": "cgroup", + "prog_id": 25, + "cgroup_id": 614, + "attach_type": "egress", + "pids": [{ + "pid": 223, + "comm": "test_progs" + } + ] + } + ] + +| +| **# bpftool link pin id 10 /sys/fs/bpf/link** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Apr 23 21:39 link diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst new file mode 100644 index 000000000..5daf3de5c --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -0,0 +1,272 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-map +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **map** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + +*COMMANDS* := +{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | +**delete** | **pin** | **help** } + +MAP COMMANDS +============= + +| **bpftool** **map** { **show** | **list** } [*MAP*] +| **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ +| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ +| [**offload_dev** *NAME*] +| **bpftool** **map dump** *MAP* +| **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] +| **bpftool** **map lookup** *MAP* [**key** *DATA*] +| **bpftool** **map getnext** *MAP* [**key** *DATA*] +| **bpftool** **map delete** *MAP* **key** *DATA* +| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] +| **bpftool** **map peek** *MAP* +| **bpftool** **map push** *MAP* **value** *VALUE* +| **bpftool** **map pop** *MAP* +| **bpftool** **map enqueue** *MAP* **value** *VALUE* +| **bpftool** **map dequeue** *MAP* +| **bpftool** **map freeze** *MAP* +| **bpftool** **map help** +| +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } +| *DATA* := { [**hex**] *BYTES* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } +| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } +| *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** +| | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** +| | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** +| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** +| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** | **arena** +| | **insn_array** | **rhash** } + +DESCRIPTION +=========== +bpftool map { show | list } [*MAP*] + Show information about loaded maps. If *MAP* is specified show information + only about given maps, otherwise list all maps currently loaded on the + system. In case of **name**, *MAP* may match several maps which will all + be shown. + + Output will start with map ID followed by map type and zero or more named + attributes (depending on kernel version). + + Since Linux 5.8 bpftool is able to discover information about processes + that hold open file descriptors (FDs) against BPF maps. On such kernels + bpftool will automatically emit this information as well. + +bpftool map create *FILE* type *TYPE* key *KEY_SIZE* value *VALUE_SIZE* entries *MAX_ENTRIES* name *NAME* [flags *FLAGS*] [inner_map *MAP*] [offload_dev *NAME*] + Create a new map with given parameters and pin it to *bpffs* as *FILE*. + + *FLAGS* should be an integer which is the combination of desired flags, + e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h UAPI header for existing + flags). + + To create maps of type array-of-maps or hash-of-maps, the **inner_map** + keyword must be used to pass an inner map. The kernel needs it to collect + metadata related to the inner maps that the new map will work with. + + Keyword **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**, *MAP* may match + several maps which will all be dumped. + +bpftool map update *MAP* [key *DATA*] [value *VALUE*] [*UPDATE_FLAGS*] + Update map entry for a given *KEY*. + + *UPDATE_FLAGS* can be one of: **any** update existing entry or add if + doesn't exit; **exist** update only if entry already exists; **noexist** + update only if entry doesn't exist. + + If the **hex** keyword is provided in front of the bytes sequence, the + bytes are parsed as hexadecimal values, even if no "0x" prefix is added. If + the keyword is not provided, then the bytes are parsed as decimal values, + unless a "0x" prefix (for hexadecimal) or a "0" prefix (for octal) is + provided. + +bpftool map lookup *MAP* [key *DATA*] + Lookup **key** in the map. + +bpftool map getnext *MAP* [key *DATA*] + Get next key. If *key* is not specified, get first key. + +bpftool map delete *MAP* key *DATA* + Remove entry from the map. + +bpftool map pin *MAP* *FILE* + Pin map *MAP* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions of *bpffs*. + +bpftool map event_pipe *MAP* [cpu *N* index *M*] + Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** map. + + Install perf rings into a perf event array map and dump output of any + **bpf_perf_event_output**\ () call in the kernel. By default read the + number of CPUs on the system and install perf ring for each CPU in the + corresponding index in the array. + + If **cpu** and **index** are specified, install perf ring for given **cpu** + at **index** in the array (single ring). + + Note that installing a perf ring into an array will silently replace any + existing ring. Any other application will stop receiving events if it + installed its rings earlier. + +bpftool map peek *MAP* + Peek next value in the queue or stack. + +bpftool map push *MAP* value *VALUE* + Push *VALUE* onto the stack. + +bpftool map pop *MAP* + Pop and print value from the stack. + +bpftool map enqueue *MAP* value *VALUE* + Enqueue *VALUE* into the queue. + +bpftool map dequeue *MAP* + Dequeue and print value from the queue. + +bpftool map freeze *MAP* + Freeze the map as read-only from user space. Entries from a frozen map can + not longer be updated or deleted with the **bpf**\ () system call. This + operation is not reversible, and the map remains immutable from user space + until its destruction. However, read and write permissions for BPF programs + to the map remain unchanged. + +bpftool map help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +-f, --bpffs + Show file names of pinned maps. + +-n, --nomount + Do not automatically attempt to mount any virtual file system (such as + tracefs or BPF virtual file system) when necessary. + +EXAMPLES +======== +**# bpftool map show** + +:: + + 10: hash name some_map flags 0x0 + key 4B value 8B max_entries 2048 memlock 167936B + pids systemd(1) + +The following three commands are equivalent: + +| +| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** +| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** +| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** + +**# bpftool map lookup id 10 key 0 1 2 3** + +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + + +**# bpftool map dump id 10** + +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + key: 0d 00 07 00 value: 02 00 00 00 01 02 03 04 + Found 2 elements + +**# bpftool map getnext id 10 key 0 1 2 3** + +:: + + key: + 00 01 02 03 + next key: + 0d 00 07 00 + +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# bpftool map pin id 10 /sys/fs/bpf/map** +| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00** + +Note that map update can also be used in order to change the program references +hold by a program array map. This can be used, for example, to change the +programs used for tail-call jumps at runtime, without having to reload the +entry-point program. Below is an example for this use case: we load a program +defining a prog array map, and with a main function that contains a tail call +to other programs that can be used either to "process" packets or to "debug" +processing. Note that the prog array map MUST be pinned into the BPF virtual +file system for the map update to work successfully, as kernel flushes prog +array maps when they have no more references from user space (and the update +would be lost as soon as bpftool exits). + +| +| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp** +| **# bpftool prog --bpffs** + +:: + + 545: xdp name main_func tag 674b4b5597193dc3 gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 240B jited 257B memlock 4096B map_ids 294 + pinned /sys/fs/bpf/foo/xdp + 546: xdp name bpf_func_process tag e369a529024751fc gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 200B jited 164B memlock 4096B + pinned /sys/fs/bpf/foo/process + 547: xdp name bpf_func_debug tag 0b597868bc7f0976 gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 200B jited 164B memlock 4096B + pinned /sys/fs/bpf/foo/debug + +**# bpftool map** + +:: + + 294: prog_array name jmp_table flags 0x0 + key 4B value 4B max_entries 1 memlock 4096B + owner_prog_type xdp owner jited + +| +| **# bpftool map pin id 294 /sys/fs/bpf/bar** +| **# bpftool map dump pinned /sys/fs/bpf/bar** + +:: + + Found 0 elements + +| +| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug** +| **# bpftool map dump pinned /sys/fs/bpf/bar** + +:: + + key: 00 00 00 00 value: 22 02 00 00 + Found 1 element diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst new file mode 100644 index 000000000..22da07087 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -0,0 +1,218 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-net +================ +------------------------------------------------------------------------------- +tool for inspection of networking related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **net** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + +NET COMMANDS +============ + +| **bpftool** **net** { **show** | **list** } [ **dev** *NAME* ] +| **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** | **prepend** ] +| **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* +| **bpftool** **net help** +| +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *ATTACH_TYPE* := { **xdp** | **xdpgeneric** | **xdpdrv** | **xdpoffload** | **tcx_ingress** | **tcx_egress** } + +DESCRIPTION +=========== +bpftool net { show | list } [ dev *NAME* ] + 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 | prepend ] + Attach bpf program *PROG* to network interface *NAME* with type specified + by *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; + **tcx_ingress** - Ingress TCX. runs on ingress net traffic; + **tcx_egress** - Egress TCX. runs on egress net traffic; + + For XDP-related attach types (**xdp**, **xdpgeneric**, **xdpdrv**, + **xdpoffload**), the **overwrite** option can be used to replace a + previously attached bpf program. + + For **tcx_ingress** and **tcx_egress** attach types, the **prepend** option + can be used to attach the program at the beginning of the chain instead of + at the end. + +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. + +bpftool net help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +EXAMPLES +======== + +| **# bpftool net** + +:: + + xdp: + eth0(2) driver id 198 + + tc: + eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act [] + eth0(2) clsact/ingress fbflow_icmp id 130246 act [] + eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726 + eth0(2) clsact/egress cls_fg_dscp id 108619 act [] + eth0(2) clsact/egress fbflow_egress id 130245 + +| +| **# bpftool -jp net** + +:: + + [{ + "xdp": [{ + "devname": "eth0", + "ifindex": 2, + "mode": "driver", + "id": 198 + } + ], + "tc": [{ + "devname": "eth0", + "ifindex": 2, + "kind": "htb", + "name": "prefix_matcher.o:[cls_prefix_matcher_htb]", + "id": 111727, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/ingress", + "name": "fbflow_icmp", + "id": 130246, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]", + "id": 111726, + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "cls_fg_dscp", + "id": 108619, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "fbflow_egress", + "id": 130245, + } + ] + } + ] + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 16 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net attach xdpdrv id 20 dev enp6s0np0 overwrite** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 20 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net detach xdpdrv dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + +| +| **# bpftool net attach tcx_ingress name tc_prog dev lo** +| **# bpftool net** +| + +:: + + tc: + lo(1) tcx/ingress tc_prog prog_id 29 + +| +| **# bpftool net attach tcx_ingress name tc_prog2 dev lo prepend** +| **# bpftool net** +| + +:: + + tc: + lo(1) tcx/ingress tc_prog2 prog_id 30 + lo(1) tcx/ingress tc_prog prog_id 29 + +| +| **# bpftool net attach tcx_ingress name tc_prog dev lo** +| **# bpftool net detach tcx_ingress dev lo** +| **# bpftool net** +| + +:: + + tc: diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst new file mode 100644 index 000000000..8c1ae55be --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -0,0 +1,69 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-perf +================ +------------------------------------------------------------------------------- +tool for inspection of perf related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **perf** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := +{ **show** | **list** | **help** } + +PERF COMMANDS +============= + +| **bpftool** **perf** { **show** | **list** } +| **bpftool** **perf help** + +DESCRIPTION +=========== +bpftool perf { show | list } + List all raw_tracepoint, tracepoint, kprobe attachment in the system. + + Output will start with process id and file descriptor in that process, + followed by bpf program id, attachment information, and attachment point. + The attachment point for raw_tracepoint/tracepoint is the trace probe name. + The attachment point for k[ret]probe is either symbol name and offset, or a + kernel virtual address. The attachment point for u[ret]probe is the file + name and the file offset. + +bpftool perf help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +EXAMPLES +======== + +| **# bpftool perf** + +:: + + pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 + pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 + pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep + pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 + +| +| **# bpftool -j perf** + +:: + + [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ + {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ + {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ + {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst new file mode 100644 index 000000000..90fa2a48c --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -0,0 +1,378 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-prog +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF progs +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **prog** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| | +{ **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | +{ **-L** | **--use-loader** } | [ { **-S** | **--sign** } **-k** <private_key.pem> **-i** <certificate.x509> ] } + +*COMMANDS* := +{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | +**loadall** | **help** } + +PROG COMMANDS +============= + +| **bpftool** **prog** { **show** | **list** } [*PROG*] +| **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**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*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] [**kernel_btf** *BTF_FILE*] +| **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] +| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] +| **bpftool** **prog tracelog** +| **bpftool** **prog tracelog** [ { **stdout** | **stderr** } *PROG* ] +| **bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] +| **bpftool** **prog profile** *PROG* [**duration** *DURATION*] *METRICs* +| **bpftool** **prog help** +| +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *TYPE* := { +| **socket** | **kprobe** | **kretprobe** | **classifier** | **action** | +| **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** | +| **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** | +| **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | +| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | +| **cgroup/connect4** | **cgroup/connect6** | **cgroup/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** | **fsession** | **freplace** | **sk_lookup** +| } +| *ATTACH_TYPE* := { +| **sk_msg_verdict** | **sk_skb_verdict** | **sk_skb_stream_verdict** | +| **sk_skb_stream_parser** | **flow_dissector** +| } +| *METRICs* := { +| **cycles** | **instructions** | **l1d_loads** | **llc_misses** | +| **itlb_misses** | **dtlb_misses** +| } + + +DESCRIPTION +=========== +bpftool prog { show | list } [*PROG*] + Show information about loaded programs. If *PROG* is specified show + information only about given programs, otherwise list all programs + currently loaded on the system. In case of **tag** or **name**, *PROG* may + match several programs which will all be shown. + + Output will start with program ID followed by program type and zero or more + named attributes (depending on kernel version). + + Since Linux 5.1 the kernel can collect statistics on BPF programs (such as + the total time spent running the program, and the number of times it was + run). If available, bpftool shows such statistics. However, the kernel does + not collect them by defaults, as it slightly impacts performance on each + program run. Activation or deactivation of the feature is performed via the + **kernel.bpf_stats_enabled** sysctl knob. + + Since Linux 5.8 bpftool is able to discover information about processes + that hold open file descriptors (FDs) against BPF programs. On such kernels + bpftool will automatically emit this information as well. + +bpftool prog dump xlated *PROG* [{ file *FILE* | [opcodes] [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** controls if raw opcodes should be printed + as well. + + In case of **tag** or **name**, *PROG* may match several programs which + will all be dumped. However, if **file** or **visual** is specified, + *PROG* must match a single program. + + If **file** is specified, the binary image will instead be written to + *FILE*. + + If **visual** is specified, control flow graph (CFG) will be built instead, + and eBPF instructions will be presented with CFG in DOT format, on standard + output. + + If the programs have line_info available, the source line will be + displayed. If **linum** is specified, the filename, line number and line + column will also be displayed. + +bpftool prog dump jited *PROG* [{ file *FILE* | [opcodes] [linum] }] + Dump jited image (host machine code) of the program. + + If *FILE* is specified image will be written to a file, otherwise it will + be disassembled and printed to stdout. *PROG* must match a single program + when **file** is specified. + + **opcodes** controls if raw opcodes will be printed. + + If the prog has line_info available, the source line will be displayed. 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*. + + Note: *FILE* must be located in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions of *bpffs*. + +bpftool prog { load | loadall } *OBJ* *PATH* [type *TYPE*] [map { idx *IDX* | name *NAME* } *MAP*] [{ offload_dev | xdpmeta_dev } *NAME*] [pinmaps *MAP_DIR*] [autoattach] [kernel_btf *BTF_FILE*] + Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog + load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog + loadall** pins all programs from the *OBJ* under *PATH* directory. **type** + is optional, if not specified program type will be inferred from section + names. By default bpftool will create new maps as declared in the ELF + object being loaded. **map** parameter allows for the reuse of existing + maps. It can be specified multiple times, each time for a different map. + *IDX* refers to index of the map to be replaced in the ELF file counting + from 0, while *NAME* allows to replace a map by name. *MAP* specifies the + map to use, referring to it by **id** or through a **pinned** file. If + **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. + + The **kernel_btf** option allows specifying an external BTF file to replace + the system's own vmlinux BTF file for CO-RE relocations. Note that any + other feature relying on BTF (such as fentry/fexit programs, struct_ops) + requires the BTF file for the actual kernel running on the host, often + exposed at /sys/kernel/btf/vmlinux. + + Note: *PATH* must be located in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions of *bpffs*. + +bpftool prog attach *PROG* *ATTACH_TYPE* [*MAP*] + Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*). Most + *ATTACH_TYPEs* require a *MAP* parameter, with the exception of + *flow_dissector* which is attached to current networking name space. + +bpftool prog detach *PROG* *ATTACH_TYPE* [*MAP*] + Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*). Most + *ATTACH_TYPEs* require a *MAP* parameter, with the exception of + *flow_dissector* which is detached from the current networking name space. + +bpftool prog tracelog + Dump the trace pipe of the system to the console (stdout). Hit <Ctrl+C> to + stop printing. BPF programs can write to this trace pipe at runtime with + the **bpf_trace_printk**\ () helper. This should be used only for debugging + purposes. For streaming data from BPF programs to user space, one can use + perf events (see also **bpftool-map**\ (8)). + +bpftool prog tracelog { stdout | stderr } *PROG* + Dump the BPF stream of the program. BPF programs can write to these streams + at runtime with the **bpf_stream_vprintk_impl**\ () kfunc. The kernel may write + error messages to the standard error stream. This facility should be used + only for debugging purposes. + +bpftool prog run *PROG* data_in *FILE* [data_out *FILE* [data_size_out *L*]] [ctx_in *FILE* [ctx_out *FILE* [ctx_size_out *M*]]] [repeat *N*] + Run BPF program *PROG* in the kernel testing infrastructure for BPF, + meaning that the program works on the data and context provided by the + user, and not on actual packets or monitored functions etc. Return value + and duration for the test run are printed out to the console. + + Input data is read from the *FILE* passed with **data_in**. If this *FILE* + is "**-**", input data is read from standard input. Input context, if any, + is read from *FILE* passed with **ctx_in**. Again, "**-**" can be used to + read from standard input, but only if standard input is not already in use + for input data. If a *FILE* is passed with **data_out**, output data is + written to that file. Similarly, output context is written to the *FILE* + passed with **ctx_out**. For both output flows, "**-**" can be used to + print to the standard output (as plain text, or JSON if relevant option was + passed). If output keywords are omitted, output data and context are + discarded. Keywords **data_size_out** and **ctx_size_out** are used to pass + the size (in bytes) for the output buffers to the kernel, although the + default of 32 kB should be more than enough for most cases. + + Keyword **repeat** is used to indicate the number of consecutive runs to + perform. Note that output data and context printed to files correspond to + the last of those runs. The duration printed out at the end of the runs is + an average over all runs performed by the command. + + Not all program types support test run. Among those which do, not all of + them can take the **ctx_in**/**ctx_out** arguments. bpftool does not + perform checks on program types. + +bpftool prog profile *PROG* [duration *DURATION*] *METRICs* + Profile *METRICs* for bpf program *PROG* for *DURATION* seconds or until + user hits <Ctrl+C>. *DURATION* is optional. If *DURATION* is not specified, + the profiling will run up to **UINT_MAX** seconds. + +bpftool prog help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +-f, --bpffs + When showing BPF programs, show file names of pinned programs. + +-m, --mapcompat + Allow loading maps with unknown map definitions. + +-n, --nomount + Do not automatically attempt to mount any virtual file system (such as + tracefs or BPF virtual file system) when necessary. + +-L, --use-loader + Load program as a "loader" program. This is useful to debug the generation + of such programs. When this option is in use, bpftool attempts to load the + programs from the object file into the kernel, but does not pin them + (therefore, the *PATH* must not be provided). + + When combined with the **-d**\ \|\ **--debug** option, additional debug + messages are generated, and the execution of the loader program will use + the **bpf_trace_printk**\ () helper to log each step of loading BTF, + creating the maps, and loading the programs (see **bpftool prog tracelog** + as a way to dump those messages). + +-S, --sign + Enable signing of the BPF program before loading. This option must be + used with **-k** and **-i**. Using this flag implicitly enables + **--use-loader**. + +-k <private_key.pem> + Path to the private key file in PEM format, required when signing. + +-i <certificate.x509> + Path to the X.509 certificate file in PEM or DER format, required when + signing. + +EXAMPLES +======== +**# bpftool prog show** + +:: + + 10: xdp name some_prog tag 005a3d2123620c8b gpl run_time_ns 81632 run_cnt 10 + loaded_at 2017-09-29T20:11:00+0000 uid 0 + xlated 528B jited 370B memlock 4096B map_ids 10 + pids systemd(1) + +**# bpftool --json --pretty prog show** + +:: + + [{ + "id": 10, + "type": "xdp", + "tag": "005a3d2123620c8b", + "gpl_compatible": true, + "run_time_ns": 81632, + "run_cnt": 10, + "loaded_at": 1506715860, + "uid": 0, + "bytes_xlated": 528, + "jited": true, + "bytes_jited": 370, + "bytes_memlock": 4096, + "map_ids": [10 + ], + "pids": [{ + "pid": 1, + "comm": "systemd" + } + ] + } + ] + +| +| **# bpftool prog dump xlated id 10 file /tmp/t** +| **$ ls -l /tmp/t** + +:: + + -rw------- 1 root root 560 Jul 22 01:42 /tmp/t + +**# bpftool prog dump jited tag 005a3d2123620c8b** + +:: + + 0: push %rbp + 1: mov %rsp,%rbp + 2: sub $0x228,%rsp + 3: sub $0x28,%rbp + 4: mov %rbx,0x0(%rbp) + +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# bpftool prog pin id 10 /sys/fs/bpf/prog** +| **# bpftool prog load ./my_prog.o /sys/fs/bpf/prog2** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Jul 22 01:43 prog + -rw------- 1 root root 0 Jul 22 01:44 prog2 + +**# bpftool prog dump jited pinned /sys/fs/bpf/prog opcodes** + +:: + + 0: push %rbp + 55 + 1: mov %rsp,%rbp + 48 89 e5 + 4: sub $0x228,%rsp + 48 81 ec 28 02 00 00 + b: sub $0x28,%rbp + 48 83 ed 28 + f: mov %rbx,0x0(%rbp) + 48 89 5d 00 + +| +| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7** +| **# bpftool prog show pinned /sys/fs/bpf/xdp1** + +:: + + 9: xdp name xdp_prog1 tag 539ec6ce11b52f98 gpl + loaded_at 2018-06-25T16:17:31-0700 uid 0 + xlated 488B jited 336B memlock 4096B map_ids 7 + +**# rm /sys/fs/bpf/xdp1** + +| +| **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses** + +:: + + 51397 run_cnt + 40176203 cycles (83.05%) + 42518139 instructions # 1.06 insns per cycle (83.39%) + 123 llc_misses # 2.89 LLC misses per million insns (83.15%) + +| +| Output below is for the trace logs. +| Run in separate terminals: +| **# bpftool prog tracelog** +| **# bpftool prog load -L -d file.o** + +:: + + bpftool-620059 [004] d... 2634685.517903: bpf_trace_printk: btf_load size 665 r=5 + bpftool-620059 [004] d... 2634685.517912: bpf_trace_printk: map_create sample_map idx 0 type 2 value_size 4 value_btf_id 0 r=6 + bpftool-620059 [004] d... 2634685.517997: bpf_trace_printk: prog_load sample insn_cnt 13 r=7 + bpftool-620059 [004] d... 2634685.517999: bpf_trace_printk: close(5) = 0 diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst new file mode 100644 index 000000000..e871b9539 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -0,0 +1,91 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================== +bpftool-struct_ops +================== +------------------------------------------------------------------------------- +tool to register/unregister/introspect BPF struct_ops +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **struct_ops** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := +{ **show** | **list** | **dump** | **register** | **unregister** | **help** } + +STRUCT_OPS COMMANDS +=================== + +| **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops register** *OBJ* [*LINK_DIR*] +| **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP* +| **bpftool** **struct_ops help** +| +| *STRUCT_OPS_MAP* := { **id** *STRUCT_OPS_MAP_ID* | **name** *STRUCT_OPS_MAP_NAME* } +| *OBJ* := /a/file/of/bpf_struct_ops.o + + +DESCRIPTION +=========== +bpftool struct_ops { show | list } [*STRUCT_OPS_MAP*] + Show brief information about the struct_ops in the system. If + *STRUCT_OPS_MAP* is specified, it shows information only for the given + struct_ops. Otherwise, it lists all struct_ops currently existing in the + system. + + Output will start with struct_ops map ID, followed by its map name and its + struct_ops's kernel type. + +bpftool struct_ops dump [*STRUCT_OPS_MAP*] + Dump details information about the struct_ops in the system. If + *STRUCT_OPS_MAP* is specified, it dumps information only for the given + struct_ops. Otherwise, it dumps all struct_ops currently existing in the + system. + +bpftool struct_ops register *OBJ* [*LINK_DIR*] + Register bpf struct_ops from *OBJ*. All struct_ops under 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. + +bpftool struct_ops help + Print short help message. + +OPTIONS +======= +.. include:: common_options.rst + +EXAMPLES +======== +**# bpftool struct_ops show** + +:: + + 100: dctcp tcp_congestion_ops + 105: cubic tcp_congestion_ops + +**# bpftool struct_ops unregister id 105** + +:: + + Unregistered tcp_congestion_ops cubic id 105 + +**# bpftool struct_ops register bpf_cubic.o** + +:: + + Registered tcp_congestion_ops cubic id 110 diff --git a/tools/bpf/bpftool/Documentation/bpftool-token.rst b/tools/bpf/bpftool/Documentation/bpftool-token.rst new file mode 100644 index 000000000..d082c499c --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-token.rst @@ -0,0 +1,64 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-token +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF tokens +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] **token** *COMMAND* + +*OPTIONS* := { |COMMON_OPTIONS| } + +*COMMANDS* := { **show** | **list** | **help** } + +TOKEN COMMANDS +=============== + +| **bpftool** **token** { **show** | **list** } +| **bpftool** **token help** +| + +DESCRIPTION +=========== +bpftool token { show | list } + List BPF token information for each *bpffs* mount point containing token + information on the system. Information include mount point path, allowed + **bpf**\ () system call commands, maps, programs, and attach types for the + token. + +bpftool prog help + Print short help message. + +OPTIONS +======== +.. include:: common_options.rst + +EXAMPLES +======== +| +| **# mkdir -p /sys/fs/bpf/token** +| **# mount -t bpf bpffs /sys/fs/bpf/token** \ +| **-o delegate_cmds=prog_load:map_create** \ +| **-o delegate_progs=kprobe** \ +| **-o delegate_attachs=xdp** +| **# bpftool token list** + +:: + + token_info /sys/fs/bpf/token + allowed_cmds: + map_create prog_load + allowed_maps: + allowed_progs: + kprobe + allowed_attachs: + xdp diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst new file mode 100644 index 000000000..f38ae5c40 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -0,0 +1,70 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +BPFTOOL +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF programs and maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + +**bpftool** [*OPTIONS*] *OBJECT* { *COMMAND* | **help** } + +**bpftool** **batch file** *FILE* + +**bpftool** **version** + +*OBJECT* := { **map** | **prog** | **link** | **cgroup** | **perf** | **net** | **feature** | +**btf** | **gen** | **struct_ops** | **iter** } + +*OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } + +*MAP-COMMANDS* := +{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | +**delete** | **pin** | **event_pipe** | **help** } + +*PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | +**load** | **attach** | **detach** | **help** } + +*LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + +*CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + +*PERF-COMMANDS* := { **show** | **list** | **help** } + +*NET-COMMANDS* := { **show** | **list** | **help** } + +*FEATURE-COMMANDS* := { **probe** | **help** } + +*BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + +*GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + +*STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + +*ITER-COMMANDS* := { **pin** | **help** } + +DESCRIPTION +=========== +*bpftool* allows for inspection and simple modification of BPF objects on the +system. + +Note that format of the output of all tools is not guaranteed to be stable and +should not be depended upon. + +OPTIONS +======= +.. include:: common_options.rst + +-m, --mapcompat + Allow loading maps with unknown map definitions. + +-n, --nomount + Do not automatically attempt to mount any virtual file system (such as + tracefs or BPF virtual file system) when necessary. diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst new file mode 100644 index 000000000..9234b9dab --- /dev/null +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -0,0 +1,23 @@ +.. 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 000000000..827e3ffb1 --- /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 new file mode 100644 index 000000000..271a7dc77 --- /dev/null +++ b/tools/bpf/bpftool/Makefile @@ -0,0 +1,346 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +include ../../scripts/Makefile.include + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +BPF_DIR = $(srctree)/tools/lib/bpf + +ifneq ($(OUTPUT),) + _OUTPUT := $(OUTPUT) +else + _OUTPUT := $(CURDIR)/ +endif +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ + +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include +LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf +LIBBPF := $(LIBBPF_OUTPUT)libbpf.a + +LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ +LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include +LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf +LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a + +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) + +$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): + $(QUIET_MKDIR)mkdir -p $@ + +$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ + DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers + +$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $< + +$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ + CFLAGS="$(LIBBPF_BOOTSTRAP_CFLAGS)" EXTRA_CFLAGS= $@ install_headers + +$(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 +CFLAGS += -Wall +CFLAGS += -Wextra +CFLAGS += -Wformat-signedness +CFLAGS += -Wno-unused-parameter +CFLAGS += -Wno-missing-field-initializers +CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(or $(OUTPUT),.) \ + -I$(LIBBPF_INCLUDE) \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi +ifneq ($(BPFTOOL_VERSION),) +CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif + +# This must be done before appending EXTRA_CFLAGS to CFLAGS to avoid +# including flags that are not applicable to the host compiler. +HOST_CFLAGS := $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ + $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) +HOST_CFLAGS += $(HOST_EXTRACFLAGS) + +ifneq ($(EXTRA_CFLAGS),) +CFLAGS += $(EXTRA_CFLAGS) +endif +ifneq ($(EXTRA_LDFLAGS),) +LDFLAGS += $(EXTRA_LDFLAGS) +endif + +HOST_LDFLAGS := $(LDFLAGS) + +# Remove warnings for libbpf bootstrap build +LIBBPF_BOOTSTRAP_CFLAGS := $(filter-out -W -Wall -Wextra -Wformat -Wformat-signedness,$(HOST_CFLAGS)) + +INSTALL ?= install +RM ?= rm -f + +FEATURE_USER = .bpftool + +# Skip optional dependencies: LLVM (JIT disasm), libbfd (fallback +# disasm), libcrypto (program signing). +SKIP_LLVM ?= +SKIP_LIBBFD ?= +SKIP_CRYPTO ?= +ifneq ($(SKIP_CRYPTO),1) + CRYPTO_LIBS := -lcrypto +endif + +ifeq ($(MAKECMDGOALS),bootstrap) +FEATURE_TESTS := libelf-zstd +FEATURE_DISPLAY := +else +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_TESTS += libelf-zstd + +FEATURE_DISPLAY := clang-bpf-co-re +FEATURE_DISPLAY += llvm +FEATURE_DISPLAY += libcap +FEATURE_DISPLAY += libbfd +FEATURE_DISPLAY += libbfd-liberty +FEATURE_DISPLAY += libbfd-liberty-z +endif + +check_feat := 1 +NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) + check_feat := 0 +endif +endif + +ifeq ($(check_feat),1) +ifeq ($(FEATURES_DUMP),) +include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif +endif + +LIBS = $(LIBBPF) -lelf $(CRYPTO_LIBS) -lz +LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf $(CRYPTO_LIBS) -lz + +ifeq ($(feature-libelf-zstd),1) +LIBS += -lzstd +LIBS_BOOTSTRAP += -lzstd +endif + +ifeq ($(feature-libcap), 1) +CFLAGS += -DUSE_LIBCAP +LIBS += -lcap +endif + +include $(wildcard $(OUTPUT)*.d) + +all: $(OUTPUT)bpftool + +SRCS := $(wildcard *.c) + +ifeq ($(feature-llvm),1) +ifneq ($(SKIP_LLVM),1) +HAS_LLVM := 1 +endif +endif + +ifeq ($(HAS_LLVM),1) + CFLAGS += -DHAVE_LLVM_SUPPORT + LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets + # llvm-config always adds -D_GNU_SOURCE, however, it may already be in CFLAGS + # (e.g. when bpftool build is called from selftests build as selftests + # Makefile includes lib.mk which sets -D_GNU_SOURCE) which would cause + # compilation error due to redefinition. Let's filter it out here. + CFLAGS += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags)) + 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 $(LLVM_CONFIG) --ldflags) +else + ifneq ($(SKIP_LIBBFD),1) + # 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 ($(feature-disassembler-init-styled), 1) + CFLAGS += -DDISASM_INIT_STYLED + endif + endif + endif # SKIP_LIBBFD +endif +ifeq ($(filter -DHAVE_LLVM_SUPPORT -DHAVE_LIBBFD_SUPPORT,$(CFLAGS)),) + # No support for JIT disassembly + SRCS := $(filter-out jit_disasm.c,$(SRCS)) +endif + +ifeq ($(SKIP_CRYPTO),1) + CFLAGS += -DBPFTOOL_WITHOUT_CRYPTO + HOST_CFLAGS += -DBPFTOOL_WITHOUT_CRYPTO + SRCS := $(filter-out sign.c,$(SRCS)) +endif + +BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool + +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o $(if $(CRYPTO_LIBS),sign.o)) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) + +OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS) + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) + +bootstrap: $(BPFTOOL_BOOTSTRAP) + +ifneq ($(VMLINUX_BTF)$(VMLINUX_H),) +ifeq ($(feature-clang-bpf-co-re),1) + +BUILD_BPF_SKELS := 1 + +ifeq ($(VMLINUX_H),) +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ +else +$(OUTPUT)vmlinux.h: $(VMLINUX_H) + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) + $(QUIET_CLANG)$(CLANG) \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ + -I$(or $(OUTPUT),.) \ + -I$(srctree)/tools/include/uapi/ \ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ + -g -O2 -Wall -fno-stack-protector \ + --target=bpf -c $< -o $@ + $(Q)$(LLVM_STRIP) -g $@ + +$(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@ + +$(OUTPUT)prog.o: $(OUTPUT)profiler.skel.h + +$(OUTPUT)pids.o: $(OUTPUT)pid_iter.skel.h + +endif +endif + +CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) + +$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + +$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) + $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(HOST_LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ + +$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@ + +$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ + +$(OUTPUT)%.o: %.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + +feature-detect-clean: + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + +clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean + $(call QUIET_CLEAN, bpftool) + $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h + $(Q)$(RM) -r -- $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) + $(call QUIET_CLEAN, core-gen) + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -r -- $(OUTPUT)feature/ + +install-bin: $(OUTPUT)bpftool + $(call QUIET_INSTALL, bpftool) + $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin + $(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool + +install: install-bin + $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir) + $(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir) + +uninstall: + $(call QUIET_UNINST, bpftool) + $(Q)$(RM) -- $(DESTDIR)$(prefix)/sbin/bpftool + $(Q)$(RM) -- $(DESTDIR)$(bash_compdir)/bpftool + +doc: + $(call descend,Documentation) + +doc-clean: + $(call descend,Documentation,clean) + +doc-install: + $(call descend,Documentation,install) + +doc-uninstall: + $(call descend,Documentation,uninstall) + +FORCE: + +.SECONDARY: +.PHONY: all FORCE bootstrap clean install-bin install uninstall +.PHONY: doc doc-clean doc-install doc-uninstall +.DEFAULT_GOAL := all + +# 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 new file mode 100644 index 000000000..75cbcb512 --- /dev/null +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -0,0 +1,1252 @@ +# bpftool(8) bash completion -*- shell-script -*- +# +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (C) 2017-2018 Netronome Systems, Inc. +# +# Author: Quentin Monnet <quentin.monnet@netronome.com> + +# Takes a list of words in argument; each one of them is added to COMPREPLY if +# it is not already present on the command line. Returns no value. +_bpftool_once_attr() +{ + local w idx found + for w in $*; do + found=0 + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ $w == ${words[idx]} ]]; then + found=1 + break + fi + done + [[ $found -eq 0 ]] && \ + COMPREPLY+=( $( compgen -W "$w" -- "$cur" ) ) + done +} + +# Takes a list of words as argument; if any of those words is present on the +# command line, return 0. Otherwise, return 1. +_bpftool_search_list() +{ + local w idx + for w in $*; do + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + [[ $w == ${words[idx]} ]] && return 0 + done + done + return 1 +} + +# Takes a list of words in argument; adds them all to COMPREPLY if none of them +# is already present on the command line. Returns no value. +_bpftool_one_of_list() +{ + _bpftool_search_list $* && return 1 + COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) ) +} + +_bpftool_get_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map ids to the list of suggestions. +_bpftool_get_map_ids_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_map_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_tags() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"name": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_btf_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_link_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp link 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_obj_map_names() +{ + local obj maps + + obj=$1 + + maps=$(objdump -j .maps -t $obj 2>/dev/null | \ + command awk '/g . .maps/ {print $NF}') + + COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) ) +} + +_bpftool_get_obj_map_idxs() +{ + local obj nmaps + + obj=$1 + + nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g . maps') + + COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) ) +} + +_sysfs_get_netdevs() +{ + COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \ + "$cur" ) ) +} + +# Retrieve type of the map that we are operating on. +_bpftool_map_guess_map_type() +{ + local keyword idx ref="" + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + case "${words[$((idx-2))]}" in + lookup|update) + keyword=${words[$((idx-1))]} + ref=${words[$((idx))]} + ;; + push) + printf "stack" + return 0 + ;; + enqueue) + printf "queue" + return 0 + ;; + esac + done + [[ -z $ref ]] && return 0 + + local type + type=$(bpftool -jp map show $keyword $ref | \ + command sed -n 's/.*"type": "\(.*\)",$/\1/p') + [[ -n $type ]] && printf $type +} + +_bpftool_map_update_get_id() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_ids_for_type stack + ;; + enqueue) + _bpftool_get_map_ids_for_type queue + ;; + *) + _bpftool_get_map_ids + ;; + esac + return 0 + fi + + # Id to complete is for a value. It can be either prog id or map id. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_ids + return 0 + ;; + prog_array) + _bpftool_get_prog_ids + return 0 + ;; + *) + return 0 + ;; + esac +} + +_bpftool_map_update_get_name() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_names_for_type stack + ;; + enqueue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + fi + + # Name to complete is for a value. It can be either prog name or map name. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_names + return 0 + ;; + prog_array) + _bpftool_get_prog_names + return 0 + ;; + *) + return 0 + ;; + esac +} + +_bpftool() +{ + local cur prev words cword comp_args + local json=0 + _init_completion -- "$@" || return + + # Deal with options + if [[ ${words[cword]} == -* ]]; then + local c='--version --json --pretty --bpffs --mapcompat --debug \ + --use-loader --base-btf --sign -i -k' + 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) + return 0 + ;; + tag) + _bpftool_get_prog_tags + return 0 + ;; + dev|offload_dev|xdpmeta_dev) + _sysfs_get_netdevs + return 0 + ;; + file|pinned|-B|--base-btf|-i|-k) + _filedir + return 0 + ;; + batch) + COMPREPLY=( $( compgen -W 'file' -- "$cur" ) ) + return 0 + ;; + esac + + # Remove all options so completions don't have to deal with them. + local i pprev + for (( i=1; i < ${#words[@]}; )); do + case ${words[i]} in + # Remove option and its argument + -B|--base-btf|-i|-k) + words=( "${words[@]:0:i}" "${words[@]:i+2}" ) + [[ $i -le $(($cword + 1)) ]] && cword=$(( cword - 2 )) + ;; + # No argument, remove option only + -*) + words=( "${words[@]:0:i}" "${words[@]:i+1}" ) + [[ $i -le $cword ]] && cword=$(( cword - 1 )) + ;; + *) + i=$(( ++i )) + ;; + esac + done + cur=${words[cword]} + prev=${words[cword - 1]} + pprev=${words[cword - 2]} + + local object=${words[1]} + + if [[ -z $object || $cword -eq 1 ]]; then + case $cur in + *) + COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \ + command sed \ + -e '/OBJECT := /!d' \ + -e 's/.*{//' \ + -e 's/}.*//' \ + -e 's/|//g' )" -- "$cur" ) ) + COMPREPLY+=( $( compgen -W 'batch help' -- "$cur" ) ) + return 0 + ;; + esac + fi + + local command=${words[2]} + [[ $command == help ]] && return 0 + + local MAP_TYPE='id pinned name' + local PROG_TYPE='id pinned tag name' + + # Completion depends on object and command in use + case $object in + prog) + # Complete id and name, only for subcommands that use prog (but no + # map) ids/names. + case $command in + show|list|dump|pin) + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + name) + _bpftool_get_prog_names + return 0 + ;; + esac + ;; + esac + + local METRIC_TYPE='cycles instructions l1d_loads llc_misses \ + itlb_misses dtlb_misses' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "xlated jited" -- \ + "$cur" ) ) + return 0 + ;; + xlated|jited) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$cur" ) ) + return 0 + ;; + *) + # "file" is not compatible with other keywords here + if _bpftool_search_list 'file'; then + return 0 + fi + if ! _bpftool_search_list 'linum opcodes visual'; then + _bpftool_once_attr 'file' + fi + _bpftool_once_attr 'linum opcodes' + if _bpftool_search_list 'xlated' && [[ "$json" == 0 ]]; then + _bpftool_once_attr 'visual' + fi + return 0 + ;; + esac + ;; + pin) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + else + _filedir + fi + return 0 + ;; + attach|detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + local BPFTOOL_PROG_ATTACH_TYPES='sk_msg_verdict \ + sk_skb_verdict sk_skb_stream_verdict sk_skb_stream_parser \ + flow_dissector' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + 7) + case $prev in + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + esac + ;; + load|loadall) + local obj + + # Propose "load/loadall" to complete "bpftool prog load", + # or bash tries to complete "load" as a filename below. + if [[ ${#words[@]} -eq 3 ]]; then + COMPREPLY=( $( compgen -W "load loadall" -- "$cur" ) ) + return 0 + fi + + if [[ ${#words[@]} -lt 6 ]]; then + _filedir + return 0 + fi + + obj=${words[3]} + + if [[ ${words[-4]} == "map" ]]; then + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + fi + if [[ ${words[-3]} == "map" ]]; then + if [[ ${words[-2]} == "idx" ]]; then + _bpftool_get_obj_map_idxs $obj + elif [[ ${words[-2]} == "name" ]]; then + _bpftool_get_obj_map_names $obj + fi + return 0 + fi + if [[ ${words[-2]} == "map" ]]; then + COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) ) + return 0 + fi + + case $prev in + type) + local BPFTOOL_PROG_LOAD_TYPES='socket kprobe \ + kretprobe classifier flow_dissector \ + action tracepoint raw_tracepoint \ + xdp perf_event cgroup/skb cgroup/sock \ + cgroup/dev lwt_in lwt_out lwt_xmit \ + lwt_seg6local sockops sk_skb sk_msg lirc_mode2 \ + cgroup/bind4 cgroup/bind6 \ + cgroup/connect4 cgroup/connect6 cgroup/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 cgroup/sock_release struct_ops \ + fentry fexit fsession freplace sk_lookup' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_LOAD_TYPES" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + return 0 + ;; + name) + _bpftool_get_map_names + return 0 + ;; + pinned|pinmaps|kernel_btf) + _filedir + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) + _bpftool_once_attr 'type pinmaps autoattach kernel_btf' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' + return 0 + ;; + esac + ;; + tracelog) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "stdout stderr" -- \ + "$cur" ) ) + return 0 + ;; + stdout|stderr) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$cur" ) ) + return 0 + ;; + *) + return 0 + ;; + esac + ;; + profile) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + COMPREPLY=( $( compgen -W "$METRIC_TYPE duration" -- "$cur" ) ) + return 0 + ;; + *) + [[ $prev == duration ]] && return 0 + _bpftool_once_attr "$METRIC_TYPE" + return 0 + ;; + esac + ;; + run) + if [[ ${#words[@]} -eq 4 ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + fi + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + name) + _bpftool_get_prog_names + return 0 + ;; + data_in|data_out|ctx_in|ctx_out) + _filedir + return 0 + ;; + repeat|data_size_out|ctx_size_out) + return 0 + ;; + *) + _bpftool_once_attr 'data_in data_out data_size_out \ + ctx_in ctx_out ctx_size_out repeat' + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help pin attach detach \ + load loadall show list tracelog run profile' -- "$cur" ) ) + ;; + esac + ;; + struct_ops) + local STRUCT_OPS_TYPE='id name' + case $command in + show|list|dump|unregister) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$STRUCT_OPS_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids_for_type struct_ops + ;; + name) + _bpftool_get_map_names_for_type struct_ops + ;; + esac + return 0 + ;; + register) + [[ $prev == $command ]] && _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'register unregister show list dump help' \ + -- "$cur" ) ) + ;; + esac + ;; + iter) + case $command in + pin) + case $prev in + $command) + _filedir + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + map) + _bpftool_one_of_list $MAP_TYPE + ;; + *) + _bpftool_once_attr 'map' + ;; + esac + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'pin help' \ + -- "$cur" ) ) + ;; + esac + ;; + map) + case $command in + show|list|dump|peek|pop|dequeue|freeze) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case "$command" in + peek) + _bpftool_get_map_ids_for_type stack + _bpftool_get_map_ids_for_type queue + ;; + pop) + _bpftool_get_map_ids_for_type stack + ;; + dequeue) + _bpftool_get_map_ids_for_type queue + ;; + *) + _bpftool_get_map_ids + ;; + esac + return 0 + ;; + name) + case "$command" in + peek) + _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_type queue + ;; + pop) + _bpftool_get_map_names_for_type stack + ;; + dequeue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + ;; + *) + return 0 + ;; + esac + ;; + create) + case $prev in + $command) + _filedir + return 0 + ;; + type) + local BPFTOOL_MAP_CREATE_TYPES="$(bpftool feature list_builtins map_types 2>/dev/null | \ + grep -v '^unspec$')" + COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) + return 0 + ;; + key|value|flags|entries) + return 0 + ;; + inner_map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + ;; + name) + case $pprev in + inner_map) + _bpftool_get_map_names + ;; + *) + return 0 + ;; + esac + ;; + *) + _bpftool_once_attr 'type 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 + ;; + lookup|getnext|delete) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + return 0 + ;; + name) + _bpftool_get_map_names + return 0 + ;; + key) + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) + ;; + *) + case $(_bpftool_map_guess_map_type) in + queue|stack) + return 0 + ;; + esac + + _bpftool_once_attr 'key' + return 0 + ;; + esac + ;; + update|push|enqueue) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_map_update_get_id $command + return 0 + ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; + key) + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) + ;; + value) + # We can have bytes, or references to a prog or a + # map, depending on the type of the map to update. + case "$(_bpftool_map_guess_map_type)" in + array_of_maps|hash_of_maps) + COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ + -- "$cur" ) ) + return 0 + ;; + prog_array) + COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ + -- "$cur" ) ) + return 0 + ;; + *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) + return 0 + ;; + esac + return 0 + ;; + *) + case $(_bpftool_map_guess_map_type) in + queue|stack) + _bpftool_once_attr 'value' + return 0; + ;; + esac + + _bpftool_once_attr 'key' + local UPDATE_FLAGS='any exist noexist' idx + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == 'value' ]]; then + # 'value' is present, but is not the last + # word i.e. we can now have UPDATE_FLAGS. + _bpftool_one_of_list "$UPDATE_FLAGS" + return 0 + fi + done + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == 'key' ]]; then + # 'key' is present, but is not the last + # word i.e. we can now have 'value'. + _bpftool_once_attr 'value' + return 0 + fi + done + + return 0 + ;; + esac + ;; + pin) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + esac + return 0 + ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids_for_type perf_event_array + return 0 + ;; + name) + _bpftool_get_map_names_for_type perf_event_array + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu index' + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'delete dump getnext help \ + lookup pin event_pipe show list update create \ + peek push enqueue pop dequeue freeze' -- \ + "$cur" ) ) + ;; + esac + ;; + btf) + local MAP_TYPE='id pinned name' + case $command in + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id map prog file" -- \ + "$cur" ) ) + return 0 + ;; + prog) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case $pprev in + prog) + _bpftool_get_prog_ids + ;; + map) + _bpftool_get_map_ids + ;; + $command) + _bpftool_get_btf_ids + ;; + esac + return 0 + ;; + name) + case $pprev in + prog) + _bpftool_get_prog_names + ;; + map) + _bpftool_get_map_names + ;; + esac + return 0 + ;; + format) + COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) + ;; + root_id) + return 0; + ;; + c) + COMPREPLY=( $( compgen -W "unsorted root_id" -- "$cur" ) ) + ;; + *) + # emit extra options + case ${words[3]} in + id) + COMPREPLY=( $( compgen -W "root_id" -- "$cur" ) ) + _bpftool_once_attr 'format' + ;; + file) + COMPREPLY=( $( compgen -W "root_id file" -- "$cur" ) ) + _bpftool_once_attr 'format' + ;; + map|prog) + if [[ ${words[3]} == "map" ]] && [[ $cword == 6 ]]; then + COMPREPLY+=( $( compgen -W "key value kv all" -- "$cur" ) ) + fi + COMPREPLY=( $( compgen -W "root_id" -- "$cur" ) ) + _bpftool_once_attr 'format' + ;; + *) + ;; + esac + return 0 + ;; + esac + ;; + show|list) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id" -- "$cur" ) ) + ;; + id) + _bpftool_get_btf_ids + ;; + esac + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help show list' \ + -- "$cur" ) ) + ;; + esac + ;; + gen) + case $command in + object) + _filedir + return 0 + ;; + skeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) + _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) + ;; + esac + ;; + cgroup) + case $command in + show|list|tree) + case $cword in + 3) + _filedir + ;; + 4) + COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) ) + ;; + esac + return 0 + ;; + attach|detach) + local BPFTOOL_CGROUP_ATTACH_TYPES="$(bpftool feature list_builtins attach_types 2>/dev/null | \ + grep '^cgroup_')" + local ATTACH_FLAGS='multi override' + # Check for $prev = $command first + if [ $prev = $command ]; then + _filedir + return 0 + # Then check for attach type. This is done outside of the + # "case $prev in" to avoid writing the whole list of attach + # types again as pattern to match (where we cannot reuse + # our variable). + elif [[ $BPFTOOL_CGROUP_ATTACH_TYPES =~ $prev ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$cur" ) ) + return 0 + fi + # case/esac for the other cases + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + *) + if ! _bpftool_search_list "$BPFTOOL_CGROUP_ATTACH_TYPES"; then + COMPREPLY=( $( compgen -W \ + "$BPFTOOL_CGROUP_ATTACH_TYPES" -- "$cur" ) ) + elif [[ "$command" == "attach" ]]; then + # We have an attach type on the command line, + # but it is not the previous word, or + # "id|pinned|tag|name" (we already checked for + # that). This should only leave the case when + # we need attach flags for "attach" commamnd. + _bpftool_one_of_list "$ATTACH_FLAGS" + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help attach detach \ + show list tree' -- "$cur" ) ) + ;; + esac + ;; + perf) + case $command in + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list' -- "$cur" ) ) + ;; + esac + ;; + net) + local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload tcx_ingress tcx_egress' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + attach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 5) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + 8) + case ${words[3]} in + tcx_ingress|tcx_egress) + _bpftool_once_attr 'prepend' + ;; + *) + _bpftool_once_attr 'overwrite' + ;; + esac + return 0 + ;; + esac + ;; + detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list attach detach' -- "$cur" ) ) + ;; + esac + ;; + feature) + case $command in + probe) + [[ $prev == "prefix" ]] && return 0 + if _bpftool_search_list 'macros'; then + _bpftool_once_attr 'prefix' + else + COMPREPLY+=( $( compgen -W 'macros' -- "$cur" ) ) + fi + _bpftool_one_of_list 'kernel dev' + _bpftool_once_attr 'full unprivileged' + return 0 + ;; + list_builtins) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'prog_types map_types \ + attach_types link_types helpers' -- "$cur" ) ) + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help list_builtins probe' -- "$cur" ) ) + ;; + esac + ;; + link) + case $command in + show|list|pin|detach) + case $prev in + id) + _bpftool_get_link_ids + return 0 + ;; + esac + ;; + esac + + local LINK_TYPE='id pinned' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + return 0 + ;; + pin|detach) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + elif [[ $pprev == "$command" ]]; then + _filedir + fi + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help pin detach show list' -- "$cur" ) ) + ;; + esac + ;; + token) + case $command in + show|list) + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help show list' -- "$cur" ) ) + ;; + esac + ;; + esac +} && +complete -F _bpftool bpftool + +# ex: ts=4 sw=4 et filetype=sh diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000..6ef908adf --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,1563 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/btf.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> + +#include "json_writer.h" +#include "main.h" + +#define KFUNC_DECL_TAG "bpf_kfunc" +#define FASTCALL_DECL_TAG "bpf_fastcall" + +#define MAX_ROOT_IDS 16 +#define MAX_BTF_FILES 64 + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", + [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", +}; + +struct sort_datum { + int index; + int type_rank; + const char *sort_name; + const char *own_name; + __u64 disambig_hash; +}; + +static const char *btf_int_enc_str(__u8 encoding) +{ + switch (encoding) { + case 0: + return "(none)"; + case BTF_INT_SIGNED: + return "SIGNED"; + case BTF_INT_CHAR: + return "CHAR"; + case BTF_INT_BOOL: + return "BOOL"; + default: + return "UNKN"; + } +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: + return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: + return "global"; + case BTF_VAR_GLOBAL_EXTERN: + return "extern"; + default: + return "(unknown)"; + } +} + +static const char *btf_func_linkage_str(const struct btf_type *t) +{ + switch (btf_vlen(t)) { + case BTF_FUNC_STATIC: + return "static"; + case BTF_FUNC_GLOBAL: + return "global"; + case BTF_FUNC_EXTERN: + return "extern"; + default: + return "(unknown)"; + } +} + +static const char *btf_str(const struct btf *btf, __u32 off) +{ + if (!off) + return "(anon)"; + return btf__name_by_offset(btf, off) ? : "(invalid)"; +} + +static int btf_kind_safe(int kind) +{ + return kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind = btf_kind(t); + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[btf_kind_safe(kind)]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[btf_kind_safe(kind)], + btf_str(btf, t->name_off)); + } + + switch (kind) { + case BTF_KIND_INT: { + __u32 v = *(__u32 *)(t + 1); + const char *enc; + + enc = btf_int_enc_str(BTF_INT_ENCODING(v)); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v)); + jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v)); + jsonw_string_field(w, "encoding", enc); + } else { + printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v), + enc); + } + break; + } + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *arr = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", arr->type); + jsonw_uint_field(w, "index_type_id", arr->index_type); + jsonw_uint_field(w, "nr_elems", arr->nelems); + } else { + printf(" type_id=%u index_type_id=%u nr_elems=%u", + arr->type, arr->index_type, arr->nelems); + } + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = (const void *)(t + 1); + __u32 i, vlen = BTF_INFO_VLEN(t->info); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "members"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, m++) { + const char *name = btf_str(btf, m->name_off); + __u32 bit_off, bit_sz; + + if (BTF_INFO_KFLAG(t->info)) { + bit_off = BTF_MEMBER_BIT_OFFSET(m->offset); + bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset); + } else { + bit_off = m->offset; + bit_sz = 0; + } + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", m->type); + jsonw_uint_field(w, "bits_offset", bit_off); + if (bit_sz) { + jsonw_uint_field(w, "bitfield_size", + bit_sz); + } + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u bits_offset=%u", + name, m->type, bit_off); + if (bit_sz) + printf(" bitfield_size=%u", bit_sz); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *v = (const void *)(t + 1); + __u32 i, vlen = BTF_INFO_VLEN(t->info); + const char *encoding; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + if (btf_kflag(t)) + jsonw_int_field(w, "val", v->val); + else + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%d", name, v->val); + else + printf("\n\t'%s' val=%u", name, (__u32)v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *v = btf_enum64(t); + __u32 i, vlen = btf_vlen(t); + const char *encoding; + + 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, + (long long)val); + else + printf("\n\t'%s' val=%lluULL", name, + (unsigned long long)val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FWD: { + const char *fwd_kind = BTF_INFO_KFLAG(t->info) ? "union" + : "struct"; + + if (json_output) + jsonw_string_field(w, "fwd_kind", fwd_kind); + else + printf(" fwd_kind=%s", fwd_kind); + break; + } + case BTF_KIND_FUNC: { + const char *linkage = btf_func_linkage_str(t); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = (const void *)(t + 1); + __u32 i, vlen = BTF_INFO_VLEN(t->info); + + if (json_output) { + jsonw_uint_field(w, "ret_type_id", t->type); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "params"); + jsonw_start_array(w); + } else { + printf(" ret_type_id=%u vlen=%u", t->type, vlen); + } + for (i = 0; i < vlen; i++, p++) { + const char *name = btf_str(btf, p->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", p->type); + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u", name, p->type); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_VAR: { + const struct btf_var *v = (const void *)(t + 1); + const char *linkage; + + linkage = btf_var_linkage_str(v->linkage); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u, linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = (const void *)(t + 1); + const struct btf_type *vt; + __u32 i, vlen = BTF_INFO_VLEN(t->info); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "vars"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "type_id", v->type); + jsonw_uint_field(w, "offset", v->offset); + jsonw_uint_field(w, "size", v->size); + jsonw_end_object(w); + } else { + printf("\n\ttype_id=%u offset=%u size=%u", + v->type, v->offset, v->size); + + if (v->type < btf__type_cnt(btf)) { + vt = btf__type_by_id(btf, v->type); + printf(" (%s '%s')", + btf_kind_str[btf_kind_safe(btf_kind(vt))], + btf_str(btf, vt->name_off)); + } + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FLOAT: { + if (json_output) + jsonw_uint_field(w, "size", t->size); + else + printf(" size=%u", t->size); + break; + } + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + break; + } + default: + break; + } + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + return 0; +} + +static int dump_btf_raw(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + const struct btf_type *t; + int i; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "types"); + jsonw_start_array(json_wtr); + } + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + t = btf__type_by_id(btf, root_type_ids[i]); + dump_btf_type(btf, root_type_ids[i], t); + } + } else { + const struct btf *base; + int cnt = btf__type_cnt(btf); + int start_id = 1; + + base = btf__base_btf(btf); + if (base) + start_id = btf__type_cnt(base); + + for (i = start_id; i < cnt; i++) { + t = btf__type_by_id(btf, i); + dump_btf_type(btf, i, t); + } + } + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + return 0; +} + +struct ptr_array { + __u32 cnt; + __u32 cap; + const void **elems; +}; + +static int ptr_array_push(const void *ptr, struct ptr_array *arr) +{ + __u32 new_cap; + void *tmp; + + if (arr->cnt == arr->cap) { + new_cap = (arr->cap ?: 16) * 2; + tmp = realloc(arr->elems, sizeof(*arr->elems) * new_cap); + if (!tmp) + return -ENOMEM; + arr->elems = tmp; + arr->cap = new_cap; + } + arr->elems[arr->cnt++] = ptr; + return 0; +} + +static void ptr_array_free(struct ptr_array *arr) +{ + free(arr->elems); +} + +static int cmp_kfuncs(const void *pa, const void *pb, void *ctx) +{ + struct btf *btf = ctx; + const struct btf_type *a = *(void **)pa; + const struct btf_type *b = *(void **)pb; + + return strcmp(btf__str_by_offset(btf, a->name_off), + btf__str_by_offset(btf, b->name_off)); +} + +static int dump_btf_kfuncs(struct btf_dump *d, const struct btf *btf) +{ + LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts); + __u32 cnt = btf__type_cnt(btf), i, j; + struct ptr_array fastcalls = {}; + struct ptr_array kfuncs = {}; + int err = 0; + + printf("\n/* BPF kfuncs */\n"); + printf("#ifndef BPF_NO_KFUNC_PROTOTYPES\n"); + + for (i = 1; i < cnt; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const struct btf_type *ft; + const char *name; + + if (!btf_is_decl_tag(t)) + continue; + + if (btf_decl_tag(t)->component_idx != -1) + continue; + + ft = btf__type_by_id(btf, t->type); + if (!btf_is_func(ft)) + continue; + + name = btf__name_by_offset(btf, t->name_off); + if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG)) == 0) { + err = ptr_array_push(ft, &kfuncs); + if (err) + goto out; + } + + if (strncmp(name, FASTCALL_DECL_TAG, sizeof(FASTCALL_DECL_TAG)) == 0) { + err = ptr_array_push(ft, &fastcalls); + if (err) + goto out; + } + } + + /* Sort kfuncs by name for improved vmlinux.h stability */ + qsort_r(kfuncs.elems, kfuncs.cnt, sizeof(*kfuncs.elems), cmp_kfuncs, (void *)btf); + for (i = 0; i < kfuncs.cnt; i++) { + const struct btf_type *t = kfuncs.elems[i]; + + printf("extern "); + + /* Assume small amount of fastcall kfuncs */ + for (j = 0; j < fastcalls.cnt; j++) { + if (fastcalls.elems[j] == t) { + printf("__bpf_fastcall "); + break; + } + } + + opts.field_name = btf__name_by_offset(btf, t->name_off); + err = btf_dump__emit_type_decl(d, t->type, &opts); + if (err) + goto out; + + printf(" __weak __ksym;\n"); + } + + printf("#endif\n\n"); + +out: + ptr_array_free(&fastcalls); + ptr_array_free(&kfuncs); + return err; +} + +static void __printf(2, 0) btf_dump_printf(void *ctx, + const char *fmt, va_list args) +{ + vfprintf(stdout, fmt, args); +} + +static int btf_type_rank(const struct btf *btf, __u32 index, bool has_name) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + const int kind = btf_kind(t); + const int max_rank = 10; + + if (t->name_off) + has_name = true; + + switch (kind) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return has_name ? 1 : 0; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + return 2; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return has_name ? 3 : max_rank; + case BTF_KIND_FUNC_PROTO: + return has_name ? 4 : max_rank; + case BTF_KIND_ARRAY: + if (has_name) + return btf_type_rank(btf, btf_array(t)->type, has_name); + return max_rank; + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + if (has_name) + return btf_type_rank(btf, t->type, has_name); + return max_rank; + default: + return max_rank; + } +} + +static const char *btf_type_sort_name(const struct btf *btf, __u32 index, bool from_ref) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + + switch (btf_kind(t)) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: { + int name_off = t->name_off; + + if (!from_ref && !name_off && btf_vlen(t)) + name_off = btf_kind(t) == BTF_KIND_ENUM64 ? + btf_enum64(t)->name_off : + btf_enum(t)->name_off; + + return btf__name_by_offset(btf, name_off); + } + case BTF_KIND_ARRAY: + return btf_type_sort_name(btf, btf_array(t)->type, true); + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + return btf_type_sort_name(btf, t->type, true); + default: + return btf__name_by_offset(btf, t->name_off); + } + return NULL; +} + +static __u64 hasher(__u64 hash, __u64 val) +{ + return hash * 31 + val; +} + +static __u64 btf_name_hasher(__u64 hash, const struct btf *btf, __u32 name_off) +{ + if (!name_off) + return hash; + + return hasher(hash, str_hash(btf__name_by_offset(btf, name_off))); +} + +static __u64 btf_type_disambig_hash(const struct btf *btf, __u32 id, bool include_members) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u32 i; + size_t hash = 0; + + hash = btf_name_hasher(hash, btf, t->name_off); + + switch (btf_kind(t)) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + for (i = 0; i < btf_vlen(t); i++) { + __u32 name_off = btf_is_enum(t) ? + btf_enum(t)[i].name_off : + btf_enum64(t)[i].name_off; + + hash = btf_name_hasher(hash, btf, name_off); + } + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + if (!include_members) + break; + for (i = 0; i < btf_vlen(t); i++) { + const struct btf_member *m = btf_members(t) + i; + + hash = btf_name_hasher(hash, btf, m->name_off); + /* resolve field type's name and hash it as well */ + hash = hasher(hash, btf_type_disambig_hash(btf, m->type, false)); + } + break; + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + hash = hasher(hash, btf_type_disambig_hash(btf, t->type, include_members)); + break; + case BTF_KIND_ARRAY: { + struct btf_array *arr = btf_array(t); + + hash = hasher(hash, arr->nelems); + hash = hasher(hash, btf_type_disambig_hash(btf, arr->type, include_members)); + break; + } + default: + break; + } + return hash; +} + +static int btf_type_compare(const void *left, const void *right) +{ + const struct sort_datum *d1 = (const struct sort_datum *)left; + const struct sort_datum *d2 = (const struct sort_datum *)right; + int r; + + r = d1->type_rank - d2->type_rank; + r = r ?: strcmp(d1->sort_name, d2->sort_name); + r = r ?: strcmp(d1->own_name, d2->own_name); + if (r) + return r; + + if (d1->disambig_hash != d2->disambig_hash) + return d1->disambig_hash < d2->disambig_hash ? -1 : 1; + + return d1->index - d2->index; +} + +static struct sort_datum *sort_btf_c(const struct btf *btf) +{ + struct sort_datum *datums; + int n; + + n = btf__type_cnt(btf); + datums = malloc(sizeof(struct sort_datum) * n); + if (!datums) + return NULL; + + for (int i = 0; i < n; ++i) { + struct sort_datum *d = datums + i; + const struct btf_type *t = btf__type_by_id(btf, i); + + d->index = i; + d->type_rank = btf_type_rank(btf, i, false); + d->sort_name = btf_type_sort_name(btf, i, false); + d->own_name = btf__name_by_offset(btf, t->name_off); + d->disambig_hash = btf_type_disambig_hash(btf, i, true); + } + + qsort(datums, n, sizeof(struct sort_datum), btf_type_compare); + + return datums; +} + +static int dump_btf_c(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt, bool sort_dump) +{ + struct sort_datum *datums = NULL; + struct btf_dump *d; + int err = 0, i; + + d = btf_dump__new(btf, btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + printf("#ifndef __VMLINUX_H__\n"); + printf("#define __VMLINUX_H__\n"); + printf("\n"); + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n"); + printf("#endif\n\n"); + printf("#ifndef __ksym\n"); + printf("#define __ksym __attribute__((section(\".ksyms\")))\n"); + printf("#endif\n\n"); + printf("#ifndef __weak\n"); + printf("#define __weak __attribute__((weak))\n"); + printf("#endif\n\n"); + printf("#ifndef __bpf_fastcall\n"); + printf("#if __has_attribute(bpf_fastcall)\n"); + printf("#define __bpf_fastcall __attribute__((bpf_fastcall))\n"); + printf("#else\n"); + printf("#define __bpf_fastcall\n"); + printf("#endif\n"); + printf("#endif\n\n"); + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + err = btf_dump__dump_type(d, root_type_ids[i]); + if (err) + goto done; + } + } else { + int cnt = btf__type_cnt(btf); + + if (sort_dump) + datums = sort_btf_c(btf); + for (i = 1; i < cnt; i++) { + int idx = datums ? datums[i].index : i; + + err = btf_dump__dump_type(d, idx); + if (err) + goto done; + } + + err = dump_btf_kfuncs(d, btf); + if (err) + goto done; + } + + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute pop\n"); + printf("#endif\n"); + printf("\n"); + printf("#endif /* __VMLINUX_H__ */\n"); + +done: + free(datums); + btf_dump__free(d); + return err; +} + +static const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; + +static struct btf *get_vmlinux_btf_from_sysfs(void) +{ + struct btf *base; + + base = btf__parse(sysfs_vmlinux, NULL); + if (!base) + p_err("failed to parse vmlinux BTF at '%s': %d\n", + sysfs_vmlinux, -errno); + + return base; +} + +#define BTF_NAME_BUFF_LEN 64 + +static bool btf_is_kernel_module(__u32 btf_id) +{ + struct bpf_btf_info btf_info = {}; + char btf_name[BTF_NAME_BUFF_LEN]; + int btf_fd; + __u32 len; + int err; + + btf_fd = bpf_btf_get_fd_by_id(btf_id); + if (btf_fd < 0) { + p_err("can't get BTF object by id (%u): %s", btf_id, strerror(errno)); + return false; + } + + len = sizeof(btf_info); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_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 struct btf *merge_btf_files(const char **files, int nr_files, + struct btf *vmlinux_base) +{ + struct btf *combined, *mod; + int ret; + + combined = btf__new_empty_split(vmlinux_base); + if (!combined) { + p_err("failed to create combined BTF: %s", strerror(errno)); + return NULL; + } + + for (int j = 0; j < nr_files; j++) { + mod = btf__parse_split(files[j], vmlinux_base); + if (!mod) { + p_err("failed to load BTF from %s: %s", files[j], strerror(errno)); + btf__free(combined); + return NULL; + } + + ret = btf__add_btf(combined, mod); + btf__free(mod); + if (ret < 0) { + p_err("failed to merge BTF from %s: %s", files[j], strerror(-ret)); + btf__free(combined); + return NULL; + } + } + + ret = btf__dedup(combined, NULL); + if (ret) { + p_err("failed to dedup combined BTF: %s", strerror(-ret)); + btf__free(combined); + return NULL; + } + + return combined; +} + +static int do_dump(int argc, char **argv) +{ + bool dump_c = false, sort_dump_c = true; + struct btf *btf = NULL, *base = NULL; + __u32 root_type_ids[MAX_ROOT_IDS]; + bool have_id_filtering; + int root_type_cnt = 0; + __u32 btf_id = -1; + const char *src; + int fd = -1; + int err = 0; + int i; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + src = GET_ARG(); + if (is_prefix(src, "map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, + BPF_F_RDONLY); + if (fd < 0) + return -1; + + btf_id = info.btf_id; + if (argc && is_prefix(*argv, "key")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "value")) { + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "all")) { + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "kv")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + } + } else if (is_prefix(src, "prog")) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + err = bpf_prog_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + goto done; + } + + btf_id = info.btf_id; + } else if (is_prefix(src, "id")) { + char *endptr; + + btf_id = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(src, "file")) { + const char sysfs_prefix[] = "/sys/kernel/btf/"; + struct btf *vmlinux_base = base_btf; + const char *files[MAX_BTF_FILES]; + int nr_files = 0; + + /* First grab our argument, filtering out the sysfs_vmlinux. */ + if (strcmp(*argv, sysfs_vmlinux) != 0) { + files[nr_files++] = *argv; + } else { + p_info("skipping %s (will be loaded as base)", *argv); + } + NEXT_ARG(); + + while (argc && is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) { + err = -EINVAL; + goto done; + } + /* Filter out any sysfs vmlinux entries. */ + if (strcmp(*argv, sysfs_vmlinux) == 0) { + p_info("skipping %s (will be loaded as base)", *argv); + NEXT_ARG(); + continue; + } + if (nr_files >= MAX_BTF_FILES) { + p_err("too many BTF files (max %d)", MAX_BTF_FILES); + err = -E2BIG; + goto done; + } + files[nr_files++] = *argv; + NEXT_ARG(); + } + + /* Auto-detect vmlinux base if any file is from sysfs */ + if (!vmlinux_base) { + for (int j = 0; j < nr_files; j++) { + if (strncmp(files[j], sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0) { + base = get_vmlinux_btf_from_sysfs(); + vmlinux_base = base; + break; + } + } + } + + /* All files were the sysfs_vmlinux, handle it like we used to */ + if (nr_files == 0) { + nr_files = 1; + files[0] = sysfs_vmlinux; + } + + if (nr_files == 1) { + btf = btf__parse_split(files[0], base ?: base_btf); + if (!btf) { + err = -errno; + p_err("failed to load BTF from %s: %s", files[0], strerror(errno)); + goto done; + } + } else { + if (!vmlinux_base) { + p_err("base BTF is required when merging multiple BTF files; use -B/--base-btf or use sysfs paths"); + err = -EINVAL; + goto done; + } + + btf = merge_btf_files(files, nr_files, vmlinux_base); + if (!btf) { + err = -errno; + goto done; + } + } + } else { + err = -1; + p_err("unrecognized BTF source specifier: '%s'", src); + goto done; + } + + have_id_filtering = !!root_type_cnt; + + while (argc) { + if (is_prefix(*argv, "format")) { + NEXT_ARG(); + if (argc < 1) { + p_err("expecting value for 'format' option\n"); + err = -EINVAL; + goto done; + } + if (strcmp(*argv, "c") == 0) { + dump_c = true; + } else if (strcmp(*argv, "raw") == 0) { + dump_c = false; + } else { + p_err("unrecognized format specifier: '%s', possible values: raw, c", + *argv); + err = -EINVAL; + goto done; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "root_id")) { + __u32 root_id; + char *end; + + if (have_id_filtering) { + p_err("cannot use root_id with other type filtering"); + err = -EINVAL; + goto done; + } else if (root_type_cnt == MAX_ROOT_IDS) { + p_err("only %d root_id are supported", MAX_ROOT_IDS); + err = -E2BIG; + goto done; + } + + NEXT_ARG(); + root_id = strtoul(*argv, &end, 0); + if (*end) { + err = -1; + p_err("can't parse %s as root ID", *argv); + goto done; + } + for (i = 0; i < root_type_cnt; i++) { + if (root_type_ids[i] == root_id) { + err = -EINVAL; + p_err("duplicate root_id %u supplied", root_id); + goto done; + } + } + root_type_ids[root_type_cnt++] = root_id; + NEXT_ARG(); + } else if (is_prefix(*argv, "unsorted")) { + sort_dump_c = false; + NEXT_ARG(); + } else { + p_err("unrecognized option: '%s'", *argv); + err = -EINVAL; + goto done; + } + } + + if (!btf) { + if (!base_btf && btf_is_kernel_module(btf_id)) { + p_info("Warning: valid base BTF was not specified with -B option, falling back to standard base BTF (%s)", + sysfs_vmlinux); + base_btf = get_vmlinux_btf_from_sysfs(); + } + + btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); + if (!btf) { + err = -errno; + p_err("get btf by id (%u): %s", btf_id, strerror(errno)); + goto done; + } + } + + /* Invalid root IDs causes half emitted boilerplate and then unclean + * exit. It's an ugly user experience, so handle common error here. + */ + for (i = 0; i < root_type_cnt; i++) { + if (root_type_ids[i] >= btf__type_cnt(btf)) { + err = -EINVAL; + p_err("invalid root ID: %u", root_type_ids[i]); + goto done; + } + } + + if (dump_c) { + if (json_output) { + p_err("JSON output for C-syntax dump is not supported"); + err = -ENOTSUP; + goto done; + } + err = dump_btf_c(btf, root_type_ids, root_type_cnt, sort_dump_c); + } else { + err = dump_btf_raw(btf, root_type_ids, root_type_cnt); + } + +done: + close(fd); + btf__free(btf); + btf__free(base); + return err; +} + +static int btf_parse_fd(int *argc, char ***argv) +{ + unsigned int id; + char *endptr; + int fd; + + if (!is_prefix(*argv[0], "id")) { + p_err("expected 'id', got: '%s'?", **argv); + return -1; + } + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + + return fd; +} + +static int +build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, + void *info, __u32 *len) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + }; + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts_ro); + __u32 btf_id, id = 0; + int err; + int fd; + + opts_ro.open_flags = BPF_F_RDONLY; + + while (true) { + switch (type) { + case BPF_OBJ_PROG: + err = bpf_prog_get_next_id(id, &id); + break; + case BPF_OBJ_MAP: + err = bpf_map_get_next_id(id, &id); + break; + default: + err = -1; + p_err("unexpected object type: %u", type); + goto err_free; + } + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next %s: %s%s", names[type], + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + fd = bpf_prog_get_fd_by_id(id); + break; + case BPF_OBJ_MAP: + fd = bpf_map_get_fd_by_id_opts(id, &opts_ro); + break; + default: + err = -1; + p_err("unexpected object type: %u", type); + goto err_free; + } + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get %s by id (%u): %s", names[type], id, + strerror(errno)); + err = -1; + goto err_free; + } + + memset(info, 0, *len); + 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], + strerror(errno)); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + btf_id = ((struct bpf_prog_info *)info)->btf_id; + break; + case BPF_OBJ_MAP: + btf_id = ((struct bpf_map_info *)info)->btf_id; + break; + default: + err = -1; + p_err("unexpected object type: %u", type); + goto err_free; + } + if (!btf_id) + continue; + + 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; + } + } + + return 0; + +err_free: + hashmap__free(tab); + return err; +} + +static int +build_btf_tables(struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct bpf_prog_info prog_info; + __u32 prog_len = sizeof(prog_info); + struct bpf_map_info map_info; + __u32 map_len = sizeof(map_info); + int err = 0; + + err = build_btf_type_table(btf_prog_table, BPF_OBJ_PROG, &prog_info, + &prog_len); + if (err) + return err; + + err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info, + &map_len); + if (err) { + hashmap__free(btf_prog_table); + return err; + } + + return 0; +} + +static void +show_btf_plain(struct bpf_btf_info *info, int fd, + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); + int n; + + printf("%u: ", info->id); + if (info->kernel_btf) + printf("name [%s] ", name); + else if (name && name[0]) + printf("name %s ", name); + else + printf("name <anon> "); + printf("size %uB", info->btf_size); + + n = 0; + hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " prog_ids " : ",", (unsigned long)entry->value); + } + + n = 0; + hashmap__for_each_key_entry(btf_map_table, entry, info->id) { + printf("%s%lu", n++ == 0 ? " map_ids " : ",", (unsigned long)entry->value); + } + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); +} + +static void +show_btf_json(struct bpf_btf_info *info, int fd, + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); + + jsonw_start_object(json_wtr); /* btf object */ + jsonw_uint_field(json_wtr, "id", info->id); + jsonw_uint_field(json_wtr, "size", info->btf_size); + + jsonw_name(json_wtr, "prog_ids"); + jsonw_start_array(json_wtr); /* prog_ids */ + hashmap__for_each_key_entry(btf_prog_table, entry, 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 */ + 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 hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[64]; + int err; + + memset(&info, 0, sizeof(info)); + err = bpf_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); + else + show_btf_plain(&info, fd, btf_prog_table, btf_map_table); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + struct hashmap *btf_prog_table; + struct hashmap *btf_map_table; + int err, fd = -1; + __u32 id = 0; + + if (argc == 2) { + fd = btf_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + } + + if (argc) { + if (fd >= 0) + close(fd); + return BAD_ARG(); + } + + btf_prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + btf_map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + if (fd >= 0) + close(fd); + p_err("failed to create hashmap for object references"); + return -1; + } + err = build_btf_tables(btf_prog_table, btf_map_table); + if (err) { + if (fd >= 0) + close(fd); + return err; + } + build_obj_refs_table(&refs_table, BPF_OBJ_BTF); + + if (fd >= 0) { + err = show_btf(fd, btf_prog_table, btf_map_table); + close(fd); + goto exit_free; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next BTF object: %s%s", + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + err = -1; + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + err = -1; + break; + } + + err = show_btf(fd, btf_prog_table, btf_map_table); + close(fd); + if (err) + break; + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + delete_obj_refs_table(refs_table); + + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [id BTF_ID]\n" + " %1$s %2$s dump BTF_SRC [format FORMAT] [root_id ROOT_ID]\n" + " %1$s %2$s help\n" + "\n" + " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] |\n" + " file FILE [file FILE]... }\n" + " FORMAT := { raw | c [unsorted] }\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-B|--base-btf} }\n" + "", + bin_name, "btf"); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { 0 } +}; + +int do_btf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c new file mode 100644 index 000000000..9dc8425b1 --- /dev/null +++ b/tools/bpf/bpftool/btf_dumper.c @@ -0,0 +1,906 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <ctype.h> +#include <stdio.h> /* for (FILE *) used by json_writer */ +#include <string.h> +#include <unistd.h> +#include <asm/byteorder.h> +#include <linux/bitops.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <bpf/btf.h> +#include <bpf/bpf.h> + +#include "json_writer.h" +#include "main.h" + +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data); + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size); + +static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, + const struct btf_type *func_proto, + __u32 prog_id) +{ + const struct btf_type *func_type; + int prog_fd = -1, func_sig_len; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *prog_name = NULL; + struct btf *prog_btf = NULL; + struct bpf_func_info finfo = {}; + __u32 finfo_rec_size; + char prog_str[1024]; + int err; + + /* Get the ptr's func_proto */ + func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0, + sizeof(prog_str)); + if (func_sig_len == -1) + return -1; + + if (!prog_id) + goto print; + + /* Get the bpf_prog's name. Obtain from func_info. */ + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + goto print; + + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + if (!info.btf_id || !info.nr_func_info) + goto print; + + finfo_rec_size = info.func_info_rec_size; + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = finfo_rec_size; + info.func_info = ptr_to_u64(&finfo); + + err = bpf_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; + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto print; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +print: + if (!prog_id) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, " 0"); + else if (prog_name) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " %s/prog_id:%u", prog_name, prog_id); + else + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " <unknown_prog_name>/prog_id:%u", prog_id); + + prog_str[sizeof(prog_str) - 1] = '\0'; + jsonw_string(d->jw, prog_str); + btf__free(prog_btf); + if (prog_fd >= 0) + close(prog_fd); + return 0; +} + +static void btf_dumper_ptr(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + unsigned long value = *(unsigned long *)data; + const struct btf_type *ptr_type; + __s32 ptr_type_id; + + if (!d->prog_id_as_func_ptr || value > UINT32_MAX) + goto print_ptr_value; + + ptr_type_id = btf__resolve_type(d->btf, t->type); + if (ptr_type_id < 0) + goto print_ptr_value; + ptr_type = btf__type_by_id(d->btf, ptr_type_id); + if (!ptr_type || !btf_is_func_proto(ptr_type)) + goto print_ptr_value; + + if (!dump_prog_id_as_func_ptr(d, ptr_type, value)) + return; + +print_ptr_value: + if (d->is_plain_text) + jsonw_printf(d->jw, "\"%p\"", (void *)value); + else + jsonw_printf(d->jw, "%lu", value); +} + +static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + int actual_type_id; + + actual_type_id = btf__resolve_type(d->btf, type_id); + if (actual_type_id < 0) + return actual_type_id; + + return btf_dumper_do_type(d, actual_type_id, bit_offset, data); +} + +static int btf_dumper_enum(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum *enums = btf_enum(t); + __s64 value; + __u32 i; + + switch (t->size) { + case 8: + value = *(__s64 *)data; + break; + case 4: + value = *(__s32 *)data; + break; + case 2: + value = *(__s16 *)data; + break; + case 1: + value = *(__s8 *)data; + break; + default: + return -EINVAL; + } + + for (i = 0; i < btf_vlen(t); i++) { + if (value == enums[i].val) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + +static int btf_dumper_enum64(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum64 *enums = btf_enum64(t); + __u32 val_lo32, val_hi32; + __u64 value; + __u32 i; + + value = *(__u64 *)data; + val_lo32 = (__u32)value; + val_hi32 = value >> 32; + + for (i = 0; i < btf_vlen(t); i++) { + if (val_lo32 == enums[i].val_lo32 && val_hi32 == enums[i].val_hi32) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + +static bool is_str_array(const struct btf *btf, const struct btf_array *arr, + const char *s) +{ + const struct btf_type *elem_type; + const char *end_s; + + if (!arr->nelems) + return false; + + elem_type = btf__type_by_id(btf, arr->type); + /* Not skipping typedef. typedef to char does not count as + * a string now. + */ + while (elem_type && btf_is_mod(elem_type)) + elem_type = btf__type_by_id(btf, elem_type->type); + + if (!elem_type || !btf_is_int(elem_type) || elem_type->size != 1) + return false; + + if (btf_int_encoding(elem_type) != BTF_INT_CHAR && + strcmp("char", btf__name_by_offset(btf, elem_type->name_off))) + return false; + + end_s = s + arr->nelems; + while (s < end_s) { + if (!*s) + return true; + if (*s <= 0x1f || *s >= 0x7f) + return false; + s++; + } + + /* '\0' is not found */ + return false; +} + +static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + struct btf_array *arr = (struct btf_array *)(t + 1); + long long elem_size; + int ret = 0; + __u32 i; + + if (is_str_array(d->btf, arr, data)) { + jsonw_string(d->jw, data); + return 0; + } + + elem_size = btf__resolve_size(d->btf, arr->type); + if (elem_size < 0) + return elem_size; + + jsonw_start_array(d->jw); + for (i = 0; i < arr->nelems; i++) { + ret = btf_dumper_do_type(d, arr->type, 0, + data + i * elem_size); + if (ret) + break; + } + + jsonw_end_array(d->jw); + return ret; +} + +static void btf_int128_print(json_writer_t *jw, const void *data, + bool is_plain_text) +{ + /* data points to a __int128 number. + * Suppose + * int128_num = *(__int128 *)data; + * The below formulas shows what upper_num and lower_num represents: + * upper_num = int128_num >> 64; + * lower_num = int128_num & 0xffffffffFFFFFFFFULL; + */ + __u64 upper_num, lower_num; + +#ifdef __BIG_ENDIAN_BITFIELD + upper_num = *(__u64 *)data; + lower_num = *(__u64 *)(data + 8); +#else + upper_num = *(__u64 *)(data + 8); + lower_num = *(__u64 *)data; +#endif + + if (is_plain_text) { + if (upper_num == 0) + jsonw_printf(jw, "0x%llx", lower_num); + else + jsonw_printf(jw, "0x%llx%016llx", upper_num, lower_num); + } else { + if (upper_num == 0) + jsonw_printf(jw, "\"0x%llx\"", lower_num); + else + jsonw_printf(jw, "\"0x%llx%016llx\"", upper_num, lower_num); + } +} + +static void btf_int128_shift(__u64 *print_num, __u16 left_shift_bits, + __u16 right_shift_bits) +{ + __u64 upper_num, lower_num; + +#ifdef __BIG_ENDIAN_BITFIELD + upper_num = print_num[0]; + lower_num = print_num[1]; +#else + upper_num = print_num[1]; + lower_num = print_num[0]; +#endif + + /* shake out un-needed bits by shift/or operations */ + if (left_shift_bits >= 64) { + upper_num = lower_num << (left_shift_bits - 64); + lower_num = 0; + } else { + upper_num = (upper_num << left_shift_bits) | + (lower_num >> (64 - left_shift_bits)); + lower_num = lower_num << left_shift_bits; + } + + if (right_shift_bits >= 64) { + lower_num = upper_num >> (right_shift_bits - 64); + upper_num = 0; + } else { + lower_num = (lower_num >> right_shift_bits) | + (upper_num << (64 - right_shift_bits)); + upper_num = upper_num >> right_shift_bits; + } + +#ifdef __BIG_ENDIAN_BITFIELD + print_num[0] = upper_num; + print_num[1] = lower_num; +#else + print_num[0] = lower_num; + print_num[1] = upper_num; +#endif +} + +static void btf_dumper_bitfield(__u32 nr_bits, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int left_shift_bits, right_shift_bits; + __u64 print_num[2] = {}; + int bytes_to_copy; + int bits_to_copy; + + bits_to_copy = bit_offset + nr_bits; + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy); + + memcpy(print_num, data, bytes_to_copy); +#if defined(__BIG_ENDIAN_BITFIELD) + left_shift_bits = bit_offset; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + left_shift_bits = 128 - bits_to_copy; +#else +#error neither big nor little endian +#endif + right_shift_bits = 128 - nr_bits; + + btf_int128_shift(print_num, left_shift_bits, right_shift_bits); + btf_int128_print(jw, print_num, is_plain_text); +} + + +static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int nr_bits = BTF_INT_BITS(int_type); + int total_bits_offset; + + /* bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 128 bits. + */ + total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + btf_dumper_bitfield(nr_bits, bit_offset, data, jw, + is_plain_text); +} + +static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + __u32 *int_type; + __u32 nr_bits; + + int_type = (__u32 *)(t + 1); + nr_bits = BTF_INT_BITS(*int_type); + /* if this is bit field */ + if (bit_offset || BTF_INT_OFFSET(*int_type) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + return 0; + } + + if (nr_bits == 128) { + btf_int128_print(jw, data, is_plain_text); + return 0; + } + + switch (BTF_INT_ENCODING(*int_type)) { + case 0: + if (BTF_INT_BITS(*int_type) == 64) + jsonw_printf(jw, "%llu", *(__u64 *)data); + else if (BTF_INT_BITS(*int_type) == 32) + jsonw_printf(jw, "%u", *(__u32 *)data); + else if (BTF_INT_BITS(*int_type) == 16) + jsonw_printf(jw, "%hu", *(__u16 *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhu", *(__u8 *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_SIGNED: + if (BTF_INT_BITS(*int_type) == 64) + jsonw_printf(jw, "%lld", *(long long *)data); + else if (BTF_INT_BITS(*int_type) == 32) + jsonw_printf(jw, "%d", *(int *)data); + else if (BTF_INT_BITS(*int_type) == 16) + jsonw_printf(jw, "%hd", *(short *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhd", *(char *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_CHAR: + if (isprint(*(char *)data)) + jsonw_printf(jw, "\"%c\"", *(char *)data); + else + if (is_plain_text) + jsonw_printf(jw, "0x%hhx", *(char *)data); + else + jsonw_printf(jw, "\"\\u00%02hhx\"", + *(char *)data); + break; + case BTF_INT_BOOL: + jsonw_bool(jw, *(bool *)data); + break; + default: + /* shouldn't happen */ + return -EINVAL; + } + + return 0; +} + +static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t; + struct btf_member *m; + const void *data_off; + int kind_flag; + int ret = 0; + int i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + kind_flag = BTF_INFO_KFLAG(t->info); + vlen = BTF_INFO_VLEN(t->info); + jsonw_start_object(d->jw); + m = (struct btf_member *)(t + 1); + + for (i = 0; i < vlen; i++) { + __u32 bit_offset = m[i].offset; + __u32 bitfield_size = 0; + + if (kind_flag) { + bitfield_size = BTF_MEMBER_BITFIELD_SIZE(bit_offset); + bit_offset = BTF_MEMBER_BIT_OFFSET(bit_offset); + } + + jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off)); + data_off = data + BITS_ROUNDDOWN_BYTES(bit_offset); + if (bitfield_size) { + btf_dumper_bitfield(bitfield_size, + BITS_PER_BYTE_MASKED(bit_offset), + data_off, d->jw, d->is_plain_text); + } else { + ret = btf_dumper_do_type(d, m[i].type, + BITS_PER_BYTE_MASKED(bit_offset), + data_off); + if (ret) + break; + } + } + + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + int ret; + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + ret = btf_dumper_do_type(d, t->type, bit_offset, data); + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + struct btf_var_secinfo *vsi; + const struct btf_type *t; + int ret = 0, i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + vsi = (struct btf_var_secinfo *)(t + 1); + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + jsonw_start_array(d->jw); + for (i = 0; i < vlen; i++) { + ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset); + if (ret) + break; + } + jsonw_end_array(d->jw); + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + return btf_dumper_int(t, bit_offset, data, d->jw, + d->is_plain_text); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return btf_dumper_struct(d, type_id, data); + case BTF_KIND_ARRAY: + return btf_dumper_array(d, type_id, data); + case BTF_KIND_ENUM: + return btf_dumper_enum(d, t, data); + case BTF_KIND_ENUM64: + return btf_dumper_enum64(d, t, data); + case BTF_KIND_PTR: + btf_dumper_ptr(d, t, data); + return 0; + case BTF_KIND_UNKN: + jsonw_printf(d->jw, "(unknown)"); + return 0; + case BTF_KIND_FWD: + /* map key or value can't be forward */ + jsonw_printf(d->jw, "(fwd-kind-invalid)"); + return -EINVAL; + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_dumper_modifier(d, type_id, bit_offset, data); + case BTF_KIND_VAR: + return btf_dumper_var(d, type_id, bit_offset, data); + case BTF_KIND_DATASEC: + return btf_dumper_datasec(d, type_id, data); + default: + jsonw_printf(d->jw, "(unsupported-kind)"); + return -EINVAL; + } +} + +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + return btf_dumper_do_type(d, type_id, 0, data); +} + +#define BTF_PRINT_ARG(...) \ + do { \ + pos += snprintf(func_sig + pos, size - pos, \ + __VA_ARGS__); \ + if (pos >= size) \ + return -1; \ + } while (0) +#define BTF_PRINT_TYPE(type) \ + do { \ + pos = __btf_dumper_type_only(btf, type, func_sig, \ + pos, size); \ + if (pos == -1) \ + return -1; \ + } while (0) + +static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, + char *func_sig, int pos, int size) +{ + const struct btf_type *proto_type; + const struct btf_array *array; + const struct btf_var *var; + const struct btf_type *t; + + if (!type_id) { + BTF_PRINT_ARG("void "); + return pos; + } + + t = btf__type_by_id(btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FLOAT: + BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_STRUCT: + BTF_PRINT_ARG("struct %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_UNION: + BTF_PRINT_ARG("union %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + BTF_PRINT_ARG("enum %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ARRAY: + array = (struct btf_array *)(t + 1); + BTF_PRINT_TYPE(array->type); + BTF_PRINT_ARG("[%u]", array->nelems); + break; + case BTF_KIND_PTR: + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG("* "); + break; + case BTF_KIND_FWD: + BTF_PRINT_ARG("%s %s ", + BTF_INFO_KFLAG(t->info) ? "union" : "struct", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_VOLATILE: + BTF_PRINT_ARG("volatile "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_CONST: + BTF_PRINT_ARG("const "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_RESTRICT: + BTF_PRINT_ARG("restrict "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_FUNC_PROTO: + pos = btf_dump_func(btf, func_sig, t, NULL, pos, size); + if (pos == -1) + return -1; + break; + case BTF_KIND_FUNC: + proto_type = btf__type_by_id(btf, t->type); + pos = btf_dump_func(btf, func_sig, proto_type, t, pos, size); + if (pos == -1) + return -1; + break; + case BTF_KIND_VAR: + var = (struct btf_var *)(t + 1); + if (var->linkage == BTF_VAR_STATIC) + BTF_PRINT_ARG("static "); + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG(" %s", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_DATASEC: + BTF_PRINT_ARG("section (\"%s\") ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_UNKN: + default: + return -1; + } + + return pos; +} + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size) +{ + int i, vlen; + + BTF_PRINT_TYPE(func_proto->type); + if (func) + BTF_PRINT_ARG("%s(", btf__name_by_offset(btf, func->name_off)); + else + BTF_PRINT_ARG("("); + vlen = BTF_INFO_VLEN(func_proto->info); + for (i = 0; i < vlen; i++) { + struct btf_param *arg = &((struct btf_param *)(func_proto + 1))[i]; + + if (i) + BTF_PRINT_ARG(", "); + if (arg->type) { + BTF_PRINT_TYPE(arg->type); + if (arg->name_off) + BTF_PRINT_ARG("%s", + btf__name_by_offset(btf, arg->name_off)); + else if (pos && func_sig[pos - 1] == ' ') + /* Remove unnecessary space for + * FUNC_PROTO that does not have + * arg->name_off + */ + func_sig[--pos] = '\0'; + } else { + BTF_PRINT_ARG("..."); + } + } + BTF_PRINT_ARG(")"); + + return pos; +} + +void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig, + int size) +{ + int err; + + func_sig[0] = '\0'; + if (!btf) + return; + + err = __btf_dumper_type_only(btf, type_id, func_sig, 0, size); + if (err < 0) + func_sig[0] = '\0'; +} + +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +void btf_dump_linfo_plain(const struct btf *btf, + const struct bpf_line_info *linfo, + const char *prefix, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (!line) + return; + line = ltrim(line); + + if (!prefix) + prefix = ""; + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + + /* More forgiving on file because linum option is + * expected to provide more info than the already + * available src line. + */ + if (!file) + file = ""; + + printf("%s%s [file:%s line_num:%u line_col:%u]\n", + prefix, line, file, + BPF_LINE_INFO_LINE_NUM(linfo->line_col), + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } else { + printf("%s%s\n", prefix, line); + } +} + +void btf_dump_linfo_json(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (line) + jsonw_string_field(json_wtr, "src", ltrim(line)); + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + + if (file) + jsonw_string_field(json_wtr, "file", file); + + if (BPF_LINE_INFO_LINE_NUM(linfo->line_col)) + jsonw_int_field(json_wtr, "line_num", + BPF_LINE_INFO_LINE_NUM(linfo->line_col)); + + if (BPF_LINE_INFO_LINE_COL(linfo->line_col)) + jsonw_int_field(json_wtr, "line_col", + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } +} + +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 new file mode 100644 index 000000000..e3785f9a6 --- /dev/null +++ b/tools/bpf/bpftool/cfg.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#include <linux/list.h> +#include <stdlib.h> +#include <string.h> + +#include "cfg.h" +#include "main.h" +#include "xlated_dumper.h" + +struct cfg { + struct list_head funcs; + int func_num; +}; + +struct func_node { + struct list_head l; + struct list_head bbs; + struct bpf_insn *start; + struct bpf_insn *end; + int idx; + int bb_num; +}; + +struct bb_node { + struct list_head l; + struct list_head e_prevs; + struct list_head e_succs; + struct bpf_insn *head; + struct bpf_insn *tail; + int idx; +}; + +#define EDGE_FLAG_EMPTY 0x0 +#define EDGE_FLAG_FALLTHROUGH 0x1 +#define EDGE_FLAG_JUMP 0x2 +struct edge_node { + struct list_head l; + struct bb_node *src; + struct bb_node *dst; + int flags; +}; + +#define ENTRY_BLOCK_INDEX 0 +#define EXIT_BLOCK_INDEX 1 +#define NUM_FIXED_BLOCKS 2 +#define func_prev(func) list_prev_entry(func, l) +#define func_next(func) list_next_entry(func, l) +#define bb_prev(bb) list_prev_entry(bb, l) +#define bb_next(bb) list_next_entry(bb, l) +#define entry_bb(func) func_first_bb(func) +#define exit_bb(func) func_last_bb(func) +#define cfg_first_func(cfg) \ + list_first_entry(&cfg->funcs, struct func_node, l) +#define cfg_last_func(cfg) \ + list_last_entry(&cfg->funcs, struct func_node, l) +#define func_first_bb(func) \ + list_first_entry(&func->bbs, struct bb_node, l) +#define func_last_bb(func) \ + list_last_entry(&func->bbs, struct bb_node, l) + +static struct func_node *cfg_append_func(struct cfg *cfg, struct bpf_insn *insn) +{ + struct func_node *new_func, *func; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func->start == insn) + return func; + else if (func->start > insn) + break; + } + + func = func_prev(func); + new_func = calloc(1, sizeof(*new_func)); + if (!new_func) { + p_err("OOM when allocating FUNC node"); + return NULL; + } + new_func->start = insn; + new_func->idx = cfg->func_num; + list_add(&new_func->l, &func->l); + cfg->func_num++; + + return new_func; +} + +static struct bb_node *func_append_bb(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *new_bb, *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + else if (bb->head > insn) + break; + } + + bb = bb_prev(bb); + new_bb = calloc(1, sizeof(*new_bb)); + if (!new_bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + new_bb->head = insn; + INIT_LIST_HEAD(&new_bb->e_prevs); + INIT_LIST_HEAD(&new_bb->e_succs); + list_add(&new_bb->l, &bb->l); + + return new_bb; +} + +static struct bb_node *func_insert_dummy_bb(struct list_head *after) +{ + struct bb_node *bb; + + bb = calloc(1, sizeof(*bb)); + if (!bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + + INIT_LIST_HEAD(&bb->e_prevs); + INIT_LIST_HEAD(&bb->e_succs); + list_add(&bb->l, after); + + return bb; +} + +static bool cfg_partition_funcs(struct cfg *cfg, struct bpf_insn *cur, + struct bpf_insn *end) +{ + struct func_node *func, *last_func; + + func = cfg_append_func(cfg, cur); + if (!func) + return true; + + for (; cur < end; cur++) { + if (cur->code != (BPF_JMP | BPF_CALL)) + continue; + if (cur->src_reg != BPF_PSEUDO_CALL) + continue; + func = cfg_append_func(cfg, cur + cur->off + 1); + if (!func) + return true; + } + + last_func = cfg_last_func(cfg); + last_func->end = end - 1; + func = cfg_first_func(cfg); + list_for_each_entry_from(func, &last_func->l, l) { + func->end = func_next(func)->start - 1; + } + + return false; +} + +static bool is_jmp_insn(__u8 code) +{ + return BPF_CLASS(code) == BPF_JMP || BPF_CLASS(code) == BPF_JMP32; +} + +static bool func_partition_bb_head(struct func_node *func) +{ + struct bpf_insn *cur, *end; + struct bb_node *bb; + + cur = func->start; + end = func->end; + INIT_LIST_HEAD(&func->bbs); + bb = func_append_bb(func, cur); + if (!bb) + return true; + + for (; cur <= end; cur++) { + if (is_jmp_insn(cur->code)) { + __u8 opcode = BPF_OP(cur->code); + + if (opcode == BPF_EXIT || opcode == BPF_CALL) + continue; + + bb = func_append_bb(func, cur + cur->off + 1); + if (!bb) + return true; + + if (opcode != BPF_JA) { + bb = func_append_bb(func, cur + 1); + if (!bb) + return true; + } + } + } + + return false; +} + +static void func_partition_bb_tail(struct func_node *func) +{ + unsigned int bb_idx = NUM_FIXED_BLOCKS; + struct bb_node *bb, *last; + + last = func_last_bb(func); + last->tail = func->end; + bb = func_first_bb(func); + list_for_each_entry_from(bb, &last->l, l) { + bb->tail = bb_next(bb)->head - 1; + bb->idx = bb_idx++; + } + + last->idx = bb_idx++; + func->bb_num = bb_idx; +} + +static bool func_add_special_bb(struct func_node *func) +{ + struct bb_node *bb; + + bb = func_insert_dummy_bb(&func->bbs); + if (!bb) + return true; + bb->idx = ENTRY_BLOCK_INDEX; + + bb = func_insert_dummy_bb(&func_last_bb(func)->l); + if (!bb) + return true; + bb->idx = EXIT_BLOCK_INDEX; + + return false; +} + +static bool func_partition_bb(struct func_node *func) +{ + if (func_partition_bb_head(func)) + return true; + + func_partition_bb_tail(func); + + return false; +} + +static struct bb_node *func_search_bb_with_head(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + } + + return NULL; +} + +static struct edge_node *new_edge(struct bb_node *src, struct bb_node *dst, + int flags) +{ + struct edge_node *e; + + e = calloc(1, sizeof(*e)); + if (!e) { + p_err("OOM when allocating edge node"); + return NULL; + } + + if (src) + e->src = src; + if (dst) + e->dst = dst; + + e->flags |= flags; + + return e; +} + +static bool func_add_bb_edges(struct func_node *func) +{ + struct bpf_insn *insn; + struct edge_node *e; + struct bb_node *bb; + + bb = entry_bb(func); + e = new_edge(bb, bb_next(bb), EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_succs); + + bb = exit_bb(func); + e = new_edge(bb_prev(bb), bb, EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_prevs); + + bb = entry_bb(func); + bb = bb_next(bb); + list_for_each_entry_from(bb, &exit_bb(func)->l, l) { + e = new_edge(bb, NULL, EDGE_FLAG_EMPTY); + if (!e) + return true; + e->src = bb; + + insn = bb->tail; + if (!is_jmp_insn(insn->code) || + BPF_OP(insn->code) == BPF_CALL || + BPF_OP(insn->code) == BPF_EXIT) { + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + continue; + } else if (BPF_OP(insn->code) == BPF_JA) { + e->dst = func_search_bb_with_head(func, + insn + insn->off + 1); + e->flags |= EDGE_FLAG_JUMP; + list_add_tail(&e->l, &bb->e_succs); + continue; + } + + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + + e = new_edge(bb, NULL, EDGE_FLAG_JUMP); + if (!e) + return true; + e->src = bb; + e->dst = func_search_bb_with_head(func, insn + insn->off + 1); + list_add_tail(&e->l, &bb->e_succs); + } + + return false; +} + +static bool cfg_build(struct cfg *cfg, struct bpf_insn *insn, unsigned int len) +{ + int cnt = len / sizeof(*insn); + struct func_node *func; + + INIT_LIST_HEAD(&cfg->funcs); + + if (cfg_partition_funcs(cfg, insn, insn + cnt)) + return true; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func_partition_bb(func) || func_add_special_bb(func)) + return true; + + if (func_add_bb_edges(func)) + return true; + } + + return false; +} + +static void cfg_destroy(struct cfg *cfg) +{ + struct func_node *func, *func2; + + list_for_each_entry_safe(func, func2, &cfg->funcs, l) { + struct bb_node *bb, *bb2; + + list_for_each_entry_safe(bb, bb2, &func->bbs, l) { + struct edge_node *e, *e2; + + list_for_each_entry_safe(e, e2, &bb->e_prevs, l) { + list_del(&e->l); + free(e); + } + + list_for_each_entry_safe(e, e2, &bb->e_succs, l) { + list_del(&e->l); + free(e); + } + + list_del(&bb->l); + free(bb); + } + + list_del(&func->l); + free(func); + } +} + +static void +draw_bb_node(struct func_node *func, struct bb_node *bb, struct dump_data *dd, + bool opcodes, bool linum) +{ + const char *shape; + + if (bb->idx == ENTRY_BLOCK_INDEX || bb->idx == EXIT_BLOCK_INDEX) + shape = "Mdiamond"; + else + shape = "record"; + + printf("\tfn_%d_bb_%d [shape=%s,style=filled,label=\"", + func->idx, bb->idx, shape); + + if (bb->idx == ENTRY_BLOCK_INDEX) { + printf("ENTRY"); + } else if (bb->idx == EXIT_BLOCK_INDEX) { + printf("EXIT"); + } else { + unsigned int start_idx; + printf("{\\\n"); + start_idx = bb->head - func->start; + dump_xlated_for_graph(dd, bb->head, bb->tail, start_idx, + opcodes, linum); + printf("}"); + } + + printf("\"];\n\n"); +} + +static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb) +{ + const char *style = "\"solid,bold\""; + const char *color = "black"; + int func_idx = func->idx; + struct edge_node *e; + int weight = 10; + + if (list_empty(&bb->e_succs)) + return; + + list_for_each_entry(e, &bb->e_succs, l) { + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=%s, color=%s, weight=%d, constraint=true", + func_idx, e->src->idx, func_idx, e->dst->idx, + style, color, weight); + printf("];\n"); + } +} + +static void +func_output_bb_def(struct func_node *func, struct dump_data *dd, + bool opcodes, bool linum) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_node(func, bb, dd, opcodes, linum); + } +} + +static void func_output_edges(struct func_node *func) +{ + int func_idx = func->idx; + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_succ_edges(func, bb); + } + + /* Add an invisible edge from ENTRY to EXIT, this is to + * improve the graph layout. + */ + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=\"invis\", constraint=true];\n", + func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX); +} + +static void +cfg_dump(struct cfg *cfg, struct dump_data *dd, bool opcodes, bool linum) +{ + struct func_node *func; + + printf("digraph \"DOT graph for eBPF program\" {\n"); + list_for_each_entry(func, &cfg->funcs, l) { + printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n", + func->idx, func->idx); + func_output_bb_def(func, dd, opcodes, linum); + func_output_edges(func); + printf("}\n"); + } + printf("}\n"); +} + +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; + + memset(&cfg, 0, sizeof(cfg)); + if (cfg_build(&cfg, insn, len)) + return; + + cfg_dump(&cfg, dd, opcodes, linum); + + cfg_destroy(&cfg); +} diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h new file mode 100644 index 000000000..b3793f4e1 --- /dev/null +++ b/tools/bpf/bpftool/cfg.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_CFG_H +#define __BPF_TOOL_CFG_H + +#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 new file mode 100644 index 000000000..ce69d1e54 --- /dev/null +++ b/tools/bpf/bpftool/cgroup.c @@ -0,0 +1,705 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2017 Facebook +// Author: Roman Gushchin <guro@fb.com> + +#undef GCC_VERSION +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#define _XOPEN_SOURCE 500 +#include <errno.h> +#include <fcntl.h> +#include <ftw.h> +#include <mntent.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> + +#include "main.h" + +static const int cgroup_attach_types[] = { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_INET_SOCK_RELEASE, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_INET4_GETPEERNAME, + BPF_CGROUP_INET6_GETPEERNAME, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_INET4_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UDP4_RECVMSG, + BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_SOCK_OPS, + BPF_CGROUP_DEVICE, + BPF_CGROUP_SYSCTL, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, + BPF_LSM_CGROUP +}; + +#define HELP_SPEC_ATTACH_FLAGS \ + "ATTACH_FLAGS := { multi | override }" + +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { cgroup_inet_ingress | cgroup_inet_egress |\n" \ + " cgroup_inet_sock_create | cgroup_sock_ops |\n" \ + " cgroup_device | cgroup_inet4_bind |\n" \ + " cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \ + " cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \ + " cgroup_inet6_connect | cgroup_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 void free_btf_vmlinux(void) +{ + btf__free(btf_vmlinux); + btf_vmlinux = NULL; + btf_vmlinux_id = 0; +} + +static enum bpf_attach_type parse_attach_type(const char *str) +{ + const char *attach_type_str; + enum bpf_attach_type type; + + for (type = 0; ; type++) { + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!attach_type_str) + break; + if (!strcmp(str, attach_type_str)) + return type; + } + + /* Also check traditionally used attach type strings. For these we keep + * allowing prefixed usage. + */ + for (type = 0; ; type++) { + attach_type_str = bpf_attach_type_input_str(type); + if (!attach_type_str) + break; + if (is_prefix(str, attach_type_str)) + return type; + } + + return __MAX_BPF_ATTACH_TYPE; +} + +static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) +{ + struct bpf_btf_info btf_info = {}; + __u32 btf_len = sizeof(btf_info); + char name[16] = {}; + int err; + int fd; + + btf_info.name = ptr_to_u64(name); + btf_info.name_len = sizeof(name); + + fd = bpf_btf_get_fd_by_id(attach_btf_obj_id); + if (fd < 0) + return; + + err = bpf_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; + + prog_fd = bpf_prog_get_fd_by_id(id); + if (prog_fd < 0) + return -1; + + 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_str) + jsonw_string_field(json_wtr, "attach_type", attach_type_str); + else + jsonw_uint_field(json_wtr, "attach_type", attach_type); + if (!(query_flags & BPF_F_QUERY_EFFECTIVE)) + jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); + jsonw_string_field(json_wtr, "name", prog_name); + if (attach_btf_name) + jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name); + jsonw_uint_field(json_wtr, "attach_btf_obj_id", info.attach_btf_obj_id); + jsonw_uint_field(json_wtr, "attach_btf_id", info.attach_btf_id); + jsonw_end_object(json_wtr); + } else { + printf("%s%-8u ", level ? " " : "", info.id); + if (attach_type_str) + printf("%-15s", attach_type_str); + else + printf("type %-10u", attach_type); + if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf(" %-15s", prog_name); + else + printf(" %-15s %-15s", attach_flags_str, prog_name); + if (attach_btf_name) + printf(" %-15s", attach_btf_name); + else if (info.attach_btf_id) + printf(" attach_btf_obj_id=%u attach_btf_id=%u", + info.attach_btf_obj_id, info.attach_btf_id); + printf("\n"); + } + + close(prog_fd); + return 0; +} + +static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) +{ + __u32 prog_cnt = 0; + int ret; + + ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL, + NULL, &prog_cnt); + if (ret) + return -1; + + return prog_cnt; +} + +static int cgroup_has_attached_progs(int cgroup_fd) +{ + unsigned int i = 0; + bool no_prog = true; + + for (i = 0; i < ARRAY_SIZE(cgroup_attach_types); i++) { + int count = count_attached_bpf_progs(cgroup_fd, cgroup_attach_types[i]); + + if (count < 0 && errno != EINVAL) + return -1; + + if (count > 0) { + no_prog = false; + break; + } + } + + return no_prog ? 0 : 1; +} + +static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_ids[1024] = {0}; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) + show_bpf_prog(prog_ids[iter], type, NULL, level); + + return 0; +} + +static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_attach_flags[1024] = {0}; + const char *attach_flags_str; + __u32 prog_ids[1024] = {0}; + char buf[32]; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + p.prog_attach_flags = prog_attach_flags; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) { + __u32 attach_flags; + + attach_flags = prog_attach_flags[iter] ?: p.attach_flags; + + switch (attach_flags) { + case BPF_F_ALLOW_MULTI: + attach_flags_str = "multi"; + break; + case BPF_F_ALLOW_OVERRIDE: + attach_flags_str = "override"; + break; + case 0: + attach_flags_str = ""; + break; + default: + snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); + attach_flags_str = buf; + } + + show_bpf_prog(prog_ids[iter], type, + attach_flags_str, level); + } + + return 0; +} + +static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + return query_flags & BPF_F_QUERY_EFFECTIVE ? + show_effective_bpf_progs(cgroup_fd, type, level) : + show_attached_bpf_progs(cgroup_fd, type, level); +} + +static int do_show(int argc, char **argv) +{ + int has_attached_progs; + const char *path; + int cgroup_fd; + int ret = -1; + unsigned int i; + + query_flags = 0; + + if (!REQ_ARGS(1)) + return -1; + path = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } + + cgroup_fd = open(path, O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", path); + goto exit; + } + + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + path, strerror(errno)); + goto exit_cgroup; + } else if (!has_attached_progs) { + ret = 0; + goto exit_cgroup; + } + + if (json_output) + jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name"); + else + printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType", + "AttachFlags", "Name"); + + btf_vmlinux = libbpf_find_kernel_btf(); + for (i = 0; i < ARRAY_SIZE(cgroup_attach_types); i++) { + /* + * Not all attach types may be supported, so it's expected, + * that some requests will fail. + * If we were able to get the show for at least one + * attach type, let's return 0. + */ + if (show_bpf_progs(cgroup_fd, cgroup_attach_types[i], 0) == 0) + ret = 0; + } + + if (json_output) + jsonw_end_array(json_wtr); + + free_btf_vmlinux(); + +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +/* + * To distinguish nftw() errors and do_show_tree_fn() errors + * and avoid duplicating error messages, let's return -2 + * from do_show_tree_fn() in case of error. + */ +#define NFTW_ERR -1 +#define SHOW_TREE_FN_ERR -2 +static int do_show_tree_fn(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftw) +{ + int has_attached_progs; + int cgroup_fd; + unsigned int i; + + if (typeflag != FTW_D) + return 0; + + cgroup_fd = open(fpath, O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s: %s", fpath, strerror(errno)); + return SHOW_TREE_FN_ERR; + } + + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } else if (!has_attached_progs) { + close(cgroup_fd); + return 0; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "cgroup", fpath); + jsonw_name(json_wtr, "programs"); + jsonw_start_array(json_wtr); + } else { + printf("%s\n", fpath); + } + + if (!btf_vmlinux) + btf_vmlinux = libbpf_find_kernel_btf(); + + for (i = 0; i < ARRAY_SIZE(cgroup_attach_types); i++) + show_bpf_progs(cgroup_fd, cgroup_attach_types[i], ftw->level); + + if (errno == EINVAL) + /* Last attach type does not support query. + * Do not report an error for this, especially because batch + * mode would stop processing commands. + */ + errno = 0; + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + + close(cgroup_fd); + + return 0; +} + +static char *find_cgroup_root(void) +{ + struct mntent *mnt; + FILE *f; + + f = fopen("/proc/mounts", "r"); + if (f == NULL) + return NULL; + + while ((mnt = getmntent(f))) { + if (strcmp(mnt->mnt_type, "cgroup2") == 0) { + fclose(f); + return strdup(mnt->mnt_dir); + } + } + + fclose(f); + return NULL; +} + +static int do_show_tree(int argc, char **argv) +{ + char *cgroup_root, *cgroup_alloced = NULL; + int ret; + + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { + p_err("cgroup v2 isn't mounted"); + return -1; + } + cgroup_root = cgroup_alloced; + } else { + cgroup_root = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } + } + + if (json_output) + jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%s\n" + "%-8s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "Name"); + else + printf("%s\n" + "%-8s %-15s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "AttachFlags", "Name"); + + switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) { + case NFTW_ERR: + p_err("can't iterate over %s: %s", cgroup_root, + strerror(errno)); + ret = -1; + break; + case SHOW_TREE_FN_ERR: + ret = -1; + break; + default: + ret = 0; + } + + if (json_output) + jsonw_end_array(json_wtr); + + free_btf_vmlinux(); + free(cgroup_alloced); + + return ret; +} + +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int cgroup_fd, prog_fd; + int attach_flags = 0; + int ret = -1; + int i; + + if (argc < 4) { + p_err("too few parameters for cgroup attach"); + goto exit; + } + + cgroup_fd = open(argv[0], O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", argv[0]); + goto exit; + } + + attach_type = parse_attach_type(argv[1]); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + goto exit_cgroup; + } + + argc -= 2; + argv = &argv[2]; + prog_fd = prog_parse_fd(&argc, &argv); + if (prog_fd < 0) + goto exit_cgroup; + + for (i = 0; i < argc; i++) { + if (is_prefix(argv[i], "multi")) { + attach_flags |= BPF_F_ALLOW_MULTI; + } else if (is_prefix(argv[i], "override")) { + attach_flags |= BPF_F_ALLOW_OVERRIDE; + } else { + p_err("unknown option: %s", argv[i]); + goto exit_cgroup; + } + } + + if (bpf_prog_attach(prog_fd, cgroup_fd, attach_type, attach_flags)) { + p_err("failed to attach program"); + goto exit_prog; + } + + if (json_output) + jsonw_null(json_wtr); + + ret = 0; + +exit_prog: + close(prog_fd); +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +static int do_detach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int prog_fd, cgroup_fd; + int ret = -1; + + if (argc < 4) { + p_err("too few parameters for cgroup detach"); + goto exit; + } + + cgroup_fd = open(argv[0], O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", argv[0]); + goto exit; + } + + attach_type = parse_attach_type(argv[1]); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + goto exit_cgroup; + } + + argc -= 2; + argv = &argv[2]; + prog_fd = prog_parse_fd(&argc, &argv); + if (prog_fd < 0) + goto exit_cgroup; + + if (bpf_prog_detach2(prog_fd, cgroup_fd, attach_type)) { + p_err("failed to detach program"); + goto exit_prog; + } + + if (json_output) + jsonw_null(json_wtr); + + ret = 0; + +exit_prog: + close(prog_fd); +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } CGROUP [**effective**]\n" + " %1$s %2$s tree [CGROUP_ROOT] [**effective**]\n" + " %1$s %2$s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" + " %1$s %2$s detach CGROUP ATTACH_TYPE PROG\n" + " %1$s %2$s help\n" + "\n" + HELP_SPEC_ATTACH_TYPES "\n" + " " HELP_SPEC_ATTACH_FLAGS "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "tree", do_show_tree }, + { "attach", do_attach }, + { "detach", do_detach }, + { "help", do_help }, + { 0 } +}; + +int do_cgroup(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c new file mode 100644 index 000000000..8bfcff9e2 --- /dev/null +++ b/tools/bpf/bpftool/common.c @@ -0,0 +1,1304 @@ +// 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 <assert.h> +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <ftw.h> +#include <libgen.h> +#include <mntent.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/mount.h> +#include <sys/resource.h> +#include <sys/stat.h> +#include <sys/vfs.h> +#include <sys/utsname.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 <zlib.h> + +#include "main.h" + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +void p_err(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "error"); + jsonw_vprintf_enquote(json_wtr, fmt, ap); + jsonw_end_object(json_wtr); + } else { + fprintf(stderr, "Error: "); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + } + va_end(ap); +} + +void p_info(const char *fmt, ...) +{ + va_list ap; + + if (json_output) + return; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + va_end(ap); +} + +static bool is_bpffs(const char *path) +{ + struct statfs st_fs; + + if (statfs(path, &st_fs) < 0) + return false; + + return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; +} + +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and programs. This was done in + * commit 97306be45fbe ("Merge branch 'switch to memcg-based memory + * accounting'"), in Linux 5.11. + * + * Libbpf also offers to probe for memcg-based accounting vs rlimit, but does + * so by checking for the availability of a given BPF helper and this has + * failed on some kernels with backports in the past, see commit 6b4384ff1088 + * ("Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK""). + * Instead, we can probe by lowering the process-based rlimit to 0, trying to + * load a BPF object, and resetting the rlimit. If the load succeeds then + * memcg-based accounting is supported. + * + * This would be too dangerous to do in the library, because multithreaded + * applications might attempt to load items while the rlimit is at 0. Given + * that bpftool is single-threaded, this is fine to do here. + */ +static bool known_to_need_rlimit(void) +{ + struct rlimit rlim_init, rlim_cur_zero = {}; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd, err; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim_init)) + return false; + + /* Drop the soft limit to zero. We maintain the hard limit to its + * current value, because lowering it would be a permanent operation + * for unprivileged users. + */ + rlim_cur_zero.rlim_max = rlim_init.rlim_max; + if (setrlimit(RLIMIT_MEMLOCK, &rlim_cur_zero)) + return false; + + /* Do not use bpf_prog_load() from libbpf here, because it calls + * bump_rlimit_memlock(), interfering with the current probe. + */ + prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + err = errno; + + /* reset soft rlimit to its initial value */ + setrlimit(RLIMIT_MEMLOCK, &rlim_init); + + if (prog_fd < 0) + return err == EPERM; + + close(prog_fd); + return false; +} + +void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + if (known_to_need_rlimit()) + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + +static int +mnt_fs(const char *target, const char *type, char *buff, size_t bufflen) +{ + bool bind_done = false; + + while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) { + if (errno != EINVAL || bind_done) { + snprintf(buff, bufflen, + "mount --make-private %s failed: %s", + target, strerror(errno)); + return -1; + } + + if (mount(target, target, "none", MS_BIND, NULL)) { + snprintf(buff, bufflen, + "mount --bind %s %s failed: %s", + target, target, strerror(errno)); + return -1; + } + + bind_done = true; + } + + if (mount(type, target, type, 0, "mode=0700")) { + snprintf(buff, bufflen, "mount -t %s %s %s failed: %s", + type, type, target, strerror(errno)); + return -1; + } + + return 0; +} + +int mount_tracefs(const char *target) +{ + char err_str[ERR_MAX_LEN]; + int err; + + err = mnt_fs(target, "tracefs", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount tracefs: %s", err_str); + } + + return err; +} + +int open_obj_pinned(const char *path, bool quiet, + const struct bpf_obj_get_opts *opts) +{ + char *pname; + int fd = -1; + + pname = strdup(path); + if (!pname) { + if (!quiet) + p_err("mem alloc failed"); + goto out_ret; + } + + fd = bpf_obj_get_opts(pname, opts); + if (fd < 0) { + if (!quiet) + p_err("bpf obj get (%s): %s", pname, + errno == EACCES && !is_bpffs(dirname(pname)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); + goto out_free; + } + +out_free: + free(pname); +out_ret: + return fd; +} + +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type, + const struct bpf_obj_get_opts *opts) +{ + enum bpf_obj_type type; + int fd; + + fd = open_obj_pinned(path, false, opts); + if (fd < 0) + return -1; + + type = get_fd_type(fd); + if (type < 0) { + close(fd); + return type; + } + if (type != exp_type) { + p_err("incorrect object type: %s", get_fd_type_name(type)); + close(fd); + return -1; + } + + return fd; +} + +int create_and_mount_bpffs_dir(const char *dir_name) +{ + char err_str[ERR_MAX_LEN]; + bool dir_exists; + int err = 0; + + if (is_bpffs(dir_name)) + return err; + + dir_exists = access(dir_name, F_OK) == 0; + + if (!dir_exists) { + char *temp_name; + char *parent_name; + + temp_name = strdup(dir_name); + if (!temp_name) { + p_err("mem alloc failed"); + return -1; + } + + parent_name = dirname(temp_name); + + if (is_bpffs(parent_name)) { + /* nothing to do if already mounted */ + free(temp_name); + return err; + } + + if (access(parent_name, F_OK) == -1) { + p_err("can't create dir '%s' to pin BPF object: parent dir '%s' doesn't exist", + dir_name, parent_name); + free(temp_name); + return -1; + } + + free(temp_name); + } + + if (block_mount) { + p_err("no BPF file system found, not mounting it due to --nomount option"); + return -1; + } + + if (!dir_exists) { + err = mkdir(dir_name, S_IRWXU); + if (err) { + p_err("failed to create dir '%s': %s", dir_name, strerror(errno)); + return err; + } + } + + err = mnt_fs(dir_name, "bpf", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount BPF file system on given dir '%s': %s", + dir_name, err_str); + + if (!dir_exists) + rmdir(dir_name); + } + + return err; +} + +int mount_bpffs_for_file(const char *file_name) +{ + char err_str[ERR_MAX_LEN]; + char *temp_name; + char *dir; + int err = 0; + + if (access(file_name, F_OK) != -1) { + p_err("can't pin BPF object: path '%s' already exists", file_name); + return -1; + } + + temp_name = strdup(file_name); + if (!temp_name) { + p_err("mem alloc failed"); + return -1; + } + + dir = dirname(temp_name); + + if (is_bpffs(dir)) + /* nothing to do if already mounted */ + goto out_free; + + if (access(dir, F_OK) == -1) { + p_err("can't pin BPF object: dir '%s' doesn't exist", dir); + err = -1; + goto out_free; + } + + if (block_mount) { + p_err("no BPF file system found, not mounting it due to --nomount option"); + err = -1; + goto out_free; + } + + err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount BPF file system to pin the object '%s': %s", + file_name, err_str); + } + +out_free: + free(temp_name); + return err; +} + +int do_pin_fd(int fd, const char *name) +{ + int err; + + err = mount_bpffs_for_file(name); + if (err) + return err; + + err = bpf_obj_pin(fd, name); + if (err) + p_err("can't pin the object (%s): %s", name, strerror(errno)); + + return err; +} + +int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) +{ + int err; + int fd; + + if (!REQ_ARGS(3)) + return -EINVAL; + + fd = get_fd(&argc, &argv); + if (fd < 0) + return fd; + + err = do_pin_fd(fd, *argv); + + close(fd); + return err; +} + +const char *get_fd_type_name(enum bpf_obj_type type) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + [BPF_OBJ_LINK] = "link", + }; + + if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) + return names[BPF_OBJ_UNKNOWN]; + + return names[type]; +} + +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + 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]; + char buf[512]; + ssize_t n; + + snprintf(path, sizeof(path), "/proc/self/fd/%d", fd); + + n = readlink(path, buf, sizeof(buf)); + if (n < 0) { + p_err("can't read link type: %s", strerror(errno)); + return -1; + } + if (n == sizeof(buf)) { + p_err("can't read link type: path too long!"); + return -1; + } + buf[n] = '\0'; + + if (strstr(buf, "bpf-map")) + return BPF_OBJ_MAP; + else if (strstr(buf, "bpf-prog")) + return BPF_OBJ_PROG; + else if (strstr(buf, "bpf-link")) + return BPF_OBJ_LINK; + + return BPF_OBJ_UNKNOWN; +} + +char *get_fdinfo(int fd, const char *key) +{ + char path[PATH_MAX]; + char *line = NULL; + size_t line_n = 0; + ssize_t n; + FILE *fdi; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); + + fdi = fopen(path, "r"); + if (!fdi) + return NULL; + + while ((n = getline(&line, &line_n, fdi)) > 0) { + char *value; + int len; + + if (!strstr(line, key)) + continue; + + fclose(fdi); + + value = strchr(line, '\t'); + if (!value || !value[1]) { + free(line); + return NULL; + } + value++; + + len = strlen(value); + memmove(line, value, len); + line[len - 1] = '\0'; + + return line; + } + + free(line); + fclose(fdi); + return NULL; +} + +void print_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "%d", data[i]); + jsonw_end_array(json_wtr); +} + +void print_hex_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]); + jsonw_end_array(json_wtr); +} + +/* extra params for nftw cb */ +static struct hashmap *build_fn_table; +static enum bpf_obj_type build_fn_type; + +static int do_build_table_cb(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftwbuf) +{ + struct bpf_prog_info pinned_info; + __u32 len = sizeof(pinned_info); + enum bpf_obj_type objtype; + int fd, err = 0; + char *path; + + if (typeflag != FTW_F) + goto out_ret; + + fd = open_obj_pinned(fpath, true, NULL); + 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; + int flags = FTW_PHYS; + int nopenfd = 16; + int err = 0; + + mntfile = setmntent("/proc/mounts", "r"); + if (!mntfile) + return -1; + + build_fn_table = tab; + build_fn_type = type; + + while ((mntent = getmntent(mntfile))) { + char *path = mntent->mnt_dir; + + if (strncmp(mntent->mnt_type, "bpf", 3) != 0) + continue; + err = nftw(path, do_build_table_cb, nopenfd, flags); + if (err) + break; + } + fclose(mntfile); + return err; +} + +void delete_pinned_obj_table(struct hashmap *map) +{ + struct hashmap_entry *entry; + size_t bkt; + + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) + free(entry->pvalue); + + hashmap__free(map); +} + +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + int cpus = libbpf_num_possible_cpus(); + + if (cpus < 0) { + p_err("Can't get # of possible cpus: %s", strerror(-cpus)); + exit(-1); + } + return cpus; +} + +static char * +ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) +{ + struct stat st; + int err; + + err = stat("/proc/self/ns/net", &st); + if (err) { + p_err("Can't stat /proc/self: %s", strerror(errno)); + return NULL; + } + + if (st.st_dev != ns_dev || st.st_ino != ns_ino) + return NULL; + + return if_indextoname(ifindex, buf); +} + +static int read_sysfs_hex_int(char *path) +{ + char vendor_id_buf[8]; + int len; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) { + p_err("Can't open %s: %s", path, strerror(errno)); + return -1; + } + + len = read(fd, vendor_id_buf, sizeof(vendor_id_buf)); + close(fd); + if (len < 0) { + p_err("Can't read %s: %s", path, strerror(errno)); + return -1; + } + if (len >= (int)sizeof(vendor_id_buf)) { + p_err("Value in %s too long", path); + return -1; + } + + vendor_id_buf[len] = 0; + + return strtol(vendor_id_buf, NULL, 0); +} + +static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name) +{ + char full_path[64]; + + snprintf(full_path, sizeof(full_path), "/sys/class/net/%s/device/%s", + devname, entry_name); + + return read_sysfs_hex_int(full_path); +} + +const char * +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt) +{ + __maybe_unused int device_id; + char devname[IF_NAMESIZE]; + int vendor_id; + + if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) { + p_err("Can't get net device name for ifindex %u: %s", ifindex, + strerror(errno)); + return NULL; + } + + vendor_id = read_sysfs_netdev_hex_int(devname, "vendor"); + if (vendor_id < 0) { + p_err("Can't get device vendor id for %s", devname); + return NULL; + } + + switch (vendor_id) { +#ifdef HAVE_LIBBFD_SUPPORT + case 0x19ee: + device_id = read_sysfs_netdev_hex_int(devname, "device"); + if (device_id != 0x4000 && + device_id != 0x6000 && + device_id != 0x6003) + p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch"); + *opt = "ctx4"; + return "NFP-6xxx"; +#endif /* HAVE_LIBBFD_SUPPORT */ + /* No NFP support in LLVM, we have no valid triple to return. */ + default: + p_err("Can't get arch name for device vendor id 0x%04x", + (unsigned int)vendor_id); + return NULL; + } +} + +void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode) +{ + char name[IF_NAMESIZE]; + + if (!ifindex) + return; + + printf(" offloaded_to "); + if (ifindex_to_name_ns(ifindex, ns_dev, ns_inode, name)) + printf("%s", name); + else + printf("ifindex %u ns_dev %llu ns_ino %llu", + ifindex, ns_dev, ns_inode); +} + +void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode) +{ + char name[IF_NAMESIZE]; + + if (!ifindex) + return; + + jsonw_name(json_wtr, "dev"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "ifindex", ifindex); + jsonw_uint_field(json_wtr, "ns_dev", ns_dev); + jsonw_uint_field(json_wtr, "ns_inode", ns_inode); + if (ifindex_to_name_ns(ifindex, ns_dev, ns_inode, name)) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_end_object(json_wtr); +} + +int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what) +{ + char *endptr; + + NEXT_ARGP(); + + if (*val) { + p_err("%s already specified", what); + return -1; + } + + *val = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as %s", **argv, what); + return -1; + } + NEXT_ARGP(); + + return 0; +} + +int __printf(2, 0) +print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args) +{ + return vfprintf(stderr, format, args); +} + +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) +{ + char prog_name[MAX_PROG_FULL_NAME]; + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_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, NULL); + 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, + const struct bpf_get_fd_by_id_opts *opts) +{ + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts_ro); + 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; + } + + /* Request a read-only fd to query the map info */ + opts_ro.open_flags = BPF_F_RDONLY; + fd = bpf_map_get_fd_by_id_opts(id, &opts_ro); + 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; + } + + /* Get an fd with the requested options, if they differ + * from the read-only options used to get the fd above. + */ + if (memcmp(opts, &opts_ro, sizeof(opts_ro))) { + close(fd); + fd = bpf_map_get_fd_by_id_opts(id, opts); + if (fd < 0) { + p_err("can't get map by id (%u): %s", id, + strerror(errno)); + goto err_close_fds; + } + } + + 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, __u32 open_flags) +{ + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); + + assert((open_flags & ~BPF_F_RDONLY) == 0); + opts.open_flags = open_flags; + + 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_opts(id, &opts); + 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, &opts); + } else if (is_prefix(**argv, "pinned")) { + char *path; + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + get_opts.file_flags = open_flags; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP, &get_opts); + 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, __u32 open_flags) +{ + 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, open_flags); + 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, __u32 open_flags) +{ + int err; + int fd; + + fd = map_parse_fd(argc, argv, open_flags); + 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_TRACE_FSESSION: return "fsession"; + 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; +} + +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) +{ + char *sep; + + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) + continue; + + sep = strchr(buf, '='); + if (!sep) + continue; + + /* Trim ending '\n' */ + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; + + *value = sep + 1; + return true; + } + + return false; +} + +int read_kernel_config(const struct kernel_config_option *requested_options, + size_t num_options, char **out_values, + const char *define_prefix) +{ + struct utsname utsn; + char path[PATH_MAX]; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; + int ret = 0; + + if (!requested_options || !out_values || num_options == 0) + return -1; + + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } + + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. + */ + file = gzopen("/proc/config.gz", "r"); + } + + if (!file) { + p_info("skipping kernel config, can't open file: %s", + strerror(errno)); + return -1; + } + + if (!gzgets(file, buf, sizeof(buf)) || !gzgets(file, buf, sizeof(buf))) { + p_info("skipping kernel config, can't read from file: %s", + strerror(errno)); + ret = -1; + goto end_parse; + } + + if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { + p_info("skipping kernel config, can't find correct file"); + ret = -1; + goto end_parse; + } + + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < num_options; i++) { + if ((define_prefix && !requested_options[i].macro_dump) || + out_values[i] || strcmp(buf, requested_options[i].name)) + continue; + + out_values[i] = strdup(value); + } + } + +end_parse: + gzclose(file); + return ret; +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c new file mode 100644 index 000000000..0f6070a0c --- /dev/null +++ b/tools/bpf/bpftool/feature.c @@ -0,0 +1,1286 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2019 Netronome Systems, Inc. */ + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <net/if.h> +#ifdef USE_LIBCAP +#include <sys/capability.h> +#endif +#include <sys/vfs.h> + +#include <linux/filter.h> +#include <linux/limits.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "main.h" + +#ifndef PROC_SUPER_MAGIC +# define PROC_SUPER_MAGIC 0x9fa0 +#endif + +enum probe_component { + COMPONENT_UNSPEC, + COMPONENT_KERNEL, + COMPONENT_DEVICE, +}; + +#define BPF_HELPER_MAKE_ENTRY(name) [BPF_FUNC_ ## name] = "bpf_" # name +static const char * const helper_name[] = { + __BPF_FUNC_MAPPER(BPF_HELPER_MAKE_ENTRY) +}; + +#undef BPF_HELPER_MAKE_ENTRY + +static bool full_mode; +#ifdef USE_LIBCAP +static bool run_as_unprivileged; +#endif + +/* Miscellaneous utility functions */ + +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + +static bool check_procfs(void) +{ + struct statfs st_fs; + + if (statfs("/proc", &st_fs) < 0) + return false; + if ((unsigned long)st_fs.f_type != PROC_SUPER_MAGIC) + return false; + + return true; +} + +static void uppercase(char *str, size_t len) +{ + size_t i; + + for (i = 0; i < len && str[i] != '\0'; i++) + str[i] = toupper(str[i]); +} + +/* Printing utility functions */ + +static void +print_bool_feature(const char *feat_name, const char *plain_name, + const char *define_name, bool res, const char *define_prefix) +{ + if (json_output) + jsonw_bool_field(json_wtr, feat_name, res); + else if (define_prefix) + printf("#define %s%sHAVE_%s\n", define_prefix, + res ? "" : "NO_", define_name); + else + printf("%s is %savailable\n", plain_name, res ? "" : "NOT "); +} + +static void print_kernel_option(const char *name, const char *value, + const char *define_prefix) +{ + char *endptr; + int res; + + if (json_output) { + if (!value) { + jsonw_null_field(json_wtr, name); + return; + } + errno = 0; + res = strtol(value, &endptr, 0); + if (!errno && *endptr == '\n') + jsonw_int_field(json_wtr, name, res); + else + jsonw_string_field(json_wtr, name, value); + } else if (define_prefix) { + if (value) + printf("#define %s%s %s\n", define_prefix, + name, value); + else + printf("/* %s%s is not set */\n", define_prefix, name); + } else { + if (value) + printf("%s is set to %s\n", name, value); + else + printf("%s is not set\n", name); + } +} + +static void +print_start_section(const char *json_title, const char *plain_title, + const char *define_comment, const char *define_prefix) +{ + if (json_output) { + jsonw_name(json_wtr, json_title); + jsonw_start_object(json_wtr); + } else if (define_prefix) { + printf("%s\n", define_comment); + } else { + printf("%s\n", plain_title); + } +} + +static void print_end_section(void) +{ + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); +} + +/* Probing functions */ + +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + +static long read_procfs(const char *path) +{ + char *endptr, *line = NULL; + size_t len = 0; + FILE *fd; + long res; + + fd = fopen(path, "r"); + if (!fd) + return -1; + + res = getline(&line, &len, fd); + fclose(fd); + if (res < 0) + return -1; + + errno = 0; + res = strtol(line, &endptr, 10); + if (errno || *line == '\0' || *endptr != '\n') + res = -1; + free(line); + + return res; +} + +static void probe_unprivileged_disabled(void) +{ + long res; + + /* No support for C-style output */ + + res = read_procfs("/proc/sys/kernel/unprivileged_bpf_disabled"); + if (json_output) { + jsonw_int_field(json_wtr, "unprivileged_bpf_disabled", res); + } else { + switch (res) { + case 0: + printf("bpf() syscall for unprivileged users is enabled\n"); + break; + case 1: + printf("bpf() syscall restricted to privileged users (without recovery)\n"); + break; + case 2: + printf("bpf() syscall restricted to privileged users (admin can change)\n"); + break; + case -1: + printf("Unable to retrieve required privileges for bpf() syscall\n"); + break; + default: + printf("bpf() syscall restriction has unknown value %ld\n", res); + } + } +} + +static void probe_jit_enable(void) +{ + long res; + + /* No support for C-style output */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_enable"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_enable", res); + } else { + switch (res) { + case 0: + printf("JIT compiler is disabled\n"); + break; + case 1: + printf("JIT compiler is enabled\n"); + break; + case 2: + printf("JIT compiler is enabled with debugging traces in kernel logs\n"); + break; + case -1: + printf("Unable to retrieve JIT-compiler status\n"); + break; + default: + printf("JIT-compiler status has unknown value %ld\n", + res); + } + } +} + +static void probe_jit_harden(void) +{ + long res; + + /* No support for C-style output */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_harden"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_harden", res); + } else { + switch (res) { + case 0: + printf("JIT compiler hardening is disabled\n"); + break; + case 1: + printf("JIT compiler hardening is enabled for unprivileged users\n"); + break; + case 2: + printf("JIT compiler hardening is enabled for all users\n"); + break; + case -1: + printf("Unable to retrieve JIT hardening status\n"); + break; + default: + printf("JIT hardening status has unknown value %ld\n", + res); + } + } +} + +static void probe_jit_kallsyms(void) +{ + long res; + + /* No support for C-style output */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_kallsyms"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_kallsyms", res); + } else { + switch (res) { + case 0: + printf("JIT compiler kallsyms exports are disabled\n"); + break; + case 1: + printf("JIT compiler kallsyms exports are enabled for root\n"); + break; + case -1: + printf("Unable to retrieve JIT kallsyms export status\n"); + break; + default: + printf("JIT kallsyms exports status has unknown value %ld\n", res); + } + } +} + +static void probe_jit_limit(void) +{ + long res; + + /* No support for C-style output */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_limit"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_limit", res); + } else { + switch (res) { + case -1: + printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); + break; + default: + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); + } + } +} + +static void probe_kernel_image_config(const char *define_prefix) +{ + struct kernel_config_option options[] = { + /* Enable BPF */ + { "CONFIG_BPF", }, + /* Enable bpf() syscall */ + { "CONFIG_BPF_SYSCALL", }, + /* Does selected architecture support eBPF JIT compiler */ + { "CONFIG_HAVE_EBPF_JIT", }, + /* Compile eBPF JIT compiler */ + { "CONFIG_BPF_JIT", }, + /* Avoid compiling eBPF interpreter (use JIT only) */ + { "CONFIG_BPF_JIT_ALWAYS_ON", }, + /* Kernel BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF", }, + /* Kernel module BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF_MODULES", }, + + /* cgroups */ + { "CONFIG_CGROUPS", }, + /* BPF programs attached to cgroups */ + { "CONFIG_CGROUP_BPF", }, + /* bpf_get_cgroup_classid() helper */ + { "CONFIG_CGROUP_NET_CLASSID", }, + /* bpf_skb_{,ancestor_}cgroup_id() helpers */ + { "CONFIG_SOCK_CGROUP_DATA", }, + + /* Tracing: attach BPF to kprobes, tracepoints, etc. */ + { "CONFIG_BPF_EVENTS", }, + /* Kprobes */ + { "CONFIG_KPROBE_EVENTS", }, + /* Uprobes */ + { "CONFIG_UPROBE_EVENTS", }, + /* Tracepoints */ + { "CONFIG_TRACING", }, + /* Syscall tracepoints */ + { "CONFIG_FTRACE_SYSCALLS", }, + /* bpf_override_return() helper support for selected arch */ + { "CONFIG_FUNCTION_ERROR_INJECTION", }, + /* bpf_override_return() helper */ + { "CONFIG_BPF_KPROBE_OVERRIDE", }, + + /* Network */ + { "CONFIG_NET", }, + /* AF_XDP sockets */ + { "CONFIG_XDP_SOCKETS", }, + /* BPF_PROG_TYPE_LWT_* and related helpers */ + { "CONFIG_LWTUNNEL_BPF", }, + /* BPF_PROG_TYPE_SCHED_ACT, TC (traffic control) actions */ + { "CONFIG_NET_ACT_BPF", }, + /* BPF_PROG_TYPE_SCHED_CLS, TC filters */ + { "CONFIG_NET_CLS_BPF", }, + /* TC clsact qdisc */ + { "CONFIG_NET_CLS_ACT", }, + /* Ingress filtering with TC */ + { "CONFIG_NET_SCH_INGRESS", }, + /* bpf_skb_get_xfrm_state() helper */ + { "CONFIG_XFRM", }, + /* bpf_get_route_realm() helper */ + { "CONFIG_IP_ROUTE_CLASSID", }, + /* BPF_PROG_TYPE_LWT_SEG6_LOCAL and related helpers */ + { "CONFIG_IPV6_SEG6_BPF", }, + /* BPF_PROG_TYPE_LIRC_MODE2 and related helpers */ + { "CONFIG_BPF_LIRC_MODE2", }, + /* BPF stream parser and BPF socket maps */ + { "CONFIG_BPF_STREAM_PARSER", }, + /* xt_bpf module for passing BPF programs to netfilter */ + { "CONFIG_NETFILTER_XT_MATCH_BPF", }, + + /* test_bpf module for BPF tests */ + { "CONFIG_TEST_BPF", }, + + /* Misc configs useful in BPF C programs */ + /* jiffies <-> sec conversion for bpf_jiffies64() helper */ + { "CONFIG_HZ", true, } + }; + char *values[ARRAY_SIZE(options)] = { }; + size_t i; + + if (read_kernel_config(options, ARRAY_SIZE(options), values, + define_prefix)) + return; + + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (define_prefix && !options[i].macro_dump) + continue; + print_kernel_option(options[i].name, values[i], define_prefix); + free(values[i]); + } +} + +static bool probe_bpf_syscall(const char *define_prefix) +{ + bool res; + + bpf_prog_load(BPF_PROG_TYPE_UNSPEC, NULL, NULL, NULL, 0, NULL); + res = (errno != ENOSYS); + + print_bool_feature("have_bpf_syscall", + "bpf() syscall", + "BPF_SYSCALL", + res, define_prefix); + + return res; +} + +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + +static void +probe_prog_type(enum bpf_prog_type prog_type, const char *prog_type_str, + bool *supported_types, const char *define_prefix, __u32 ifindex) +{ + char feat_name[128], plain_desc[128], define_name[128]; + const char *plain_comment = "eBPF program_type "; + size_t maxlen; + bool res; + + if (ifindex) { + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL) > 0; + } + +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for unprivileged users + * check that we did not fail because of insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + + supported_types[prog_type] |= res; + + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; + if (strlen(prog_type_str) > maxlen) { + p_info("program type name too long"); + return; + } + + sprintf(feat_name, "have_%s_prog_type", prog_type_str); + sprintf(define_name, "%s_prog_type", prog_type_str); + uppercase(define_name, sizeof(define_name)); + sprintf(plain_desc, "%s%s", plain_comment, prog_type_str); + print_bool_feature(feat_name, plain_desc, define_name, res, + define_prefix); +} + +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + +static void +probe_map_type(enum bpf_map_type map_type, char const *map_type_str, + const char *define_prefix, __u32 ifindex) +{ + char feat_name[128], plain_desc[128], define_name[128]; + const char *plain_comment = "eBPF map_type "; + size_t maxlen; + bool res; + + if (ifindex) { + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } + + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL) > 0; + } + + /* Probe result depends on the success of map creation, no additional + * check required for unprivileged users + */ + + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; + if (strlen(map_type_str) > maxlen) { + p_info("map type name too long"); + return; + } + + sprintf(feat_name, "have_%s_map_type", map_type_str); + sprintf(define_name, "%s_map_type", map_type_str); + uppercase(define_name, sizeof(define_name)); + sprintf(plain_desc, "%s%s", plain_comment, map_type_str); + print_bool_feature(feat_name, plain_desc, define_name, res, + define_prefix); +} + +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ") && + !grep(buf, "program of this type cannot use helper "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + +static bool +probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, + const char *define_prefix, unsigned int id, + const char *ptype_name, __u32 ifindex) +{ + bool res = false; + + if (supported_type) { + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL) > 0; +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for + * unprivileged users check that we did not fail because of + * insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + } + + if (json_output) { + if (res) + jsonw_string(json_wtr, helper_name[id]); + } else if (define_prefix) { + printf("#define %sBPF__PROG_TYPE_%s__HELPER_%s %s\n", + define_prefix, ptype_name, helper_name[id], + res ? "1" : "0"); + } else { + if (res) + printf("\n\t- %s", helper_name[id]); + } + + return res; +} + +static void +probe_helpers_for_progtype(enum bpf_prog_type prog_type, + const char *prog_type_str, bool supported_type, + const char *define_prefix, __u32 ifindex) +{ + char feat_name[128]; + unsigned int id; + bool probe_res = false; + + if (ifindex) + /* Only test helpers for offload-able program types */ + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + if (json_output) { + sprintf(feat_name, "%s_available_helpers", prog_type_str); + jsonw_name(json_wtr, feat_name); + jsonw_start_array(json_wtr); + } else if (!define_prefix) { + printf("eBPF helpers supported for program type %s:", + prog_type_str); + } + + for (id = 1; id < ARRAY_SIZE(helper_name); id++) { + /* Skip helper functions which emit dmesg messages when not in + * the full mode. + */ + switch (id) { + case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: + case BPF_FUNC_probe_write_user: + if (!full_mode) + continue; + fallthrough; + default: + probe_res |= probe_helper_for_progtype(prog_type, supported_type, + define_prefix, id, prog_type_str, + ifindex); + } + } + + if (json_output) + jsonw_end_array(json_wtr); + else if (!define_prefix) { + printf("\n"); + if (!probe_res) { + if (!supported_type) + printf("\tProgram type not supported\n"); + else + printf("\tCould not determine which helpers are available\n"); + } + } + + +} + +static void +probe_misc_feature(struct bpf_insn *insns, size_t len, + const char *define_prefix, __u32 ifindex, + const char *feat_name, const char *plain_name, + const char *define_name) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_ifindex = ifindex, + ); + bool res; + int fd; + + errno = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, len, &opts); + res = fd >= 0 || !errno; + + if (fd >= 0) + close(fd); + + print_bool_feature(feat_name, plain_name, define_name, res, + define_prefix); +} + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_large_insn_limit", + "Large program size limit", + "LARGE_INSN_LIMIT"); +} + +/* + * Probe for bounded loop support introduced in commit 2589726d12a1 + * ("bpf: introduce bounded loops"). + */ +static void +probe_bounded_loops(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_bounded_loops", + "Bounded loop support", + "BOUNDED_LOOPS"); +} + +/* + * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b + * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions"). + */ +static void +probe_v2_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v2_isa_extension", + "ISA extension v2", + "V2_ISA_EXTENSION"); +} + +/* + * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6 + * ("bpf: verifier support JMP32"). + */ +static void +probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v3_isa_extension", + "ISA extension v3", + "V3_ISA_EXTENSION"); +} + +/* + * Probe for the v4 instruction set extension introduced in commit 1f9a1ea821ff + * ("bpf: Support new sign-extension load insns"). + */ +static void +probe_v4_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[5] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JEQ, BPF_REG_0, 1, 1), + BPF_JMP32_A(1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v4_isa_extension", + "ISA extension v4", + "V4_ISA_EXTENSION"); +} + +static void +section_system_config(enum probe_component target, const char *define_prefix) +{ + switch (target) { + case COMPONENT_KERNEL: + case COMPONENT_UNSPEC: + print_start_section("system_config", + "Scanning system configuration...", + "/*** Misc kernel config items ***/", + define_prefix); + if (!define_prefix) { + if (check_procfs()) { + probe_unprivileged_disabled(); + probe_jit_enable(); + probe_jit_harden(); + probe_jit_kallsyms(); + probe_jit_limit(); + } else { + p_info("/* procfs not mounted, skipping related probes */"); + } + } + probe_kernel_image_config(define_prefix); + print_end_section(); + break; + default: + break; + } +} + +static bool section_syscall_config(const char *define_prefix) +{ + bool res; + + print_start_section("syscall_config", + "Scanning system call availability...", + "/*** System call availability ***/", + define_prefix); + res = probe_bpf_syscall(define_prefix); + print_end_section(); + + return res; +} + +static void +section_program_types(bool *supported_types, const char *define_prefix, + __u32 ifindex) +{ + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; + + print_start_section("program_types", + "Scanning eBPF program types...", + "/*** eBPF program types ***/", + define_prefix); + + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_prog_type(prog_type, prog_type_str, supported_types, define_prefix, + ifindex); + } + + print_end_section(); +} + +static void section_map_types(const char *define_prefix, __u32 ifindex) +{ + unsigned int map_type = BPF_MAP_TYPE_UNSPEC; + const char *map_type_str; + + print_start_section("map_types", + "Scanning eBPF map types...", + "/*** eBPF map types ***/", + define_prefix); + + while (true) { + map_type++; + map_type_str = libbpf_bpf_map_type_str(map_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!map_type_str) + break; + + probe_map_type(map_type, map_type_str, define_prefix, ifindex); + } + + print_end_section(); +} + +static void +section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) +{ + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; + + print_start_section("helpers", + "Scanning eBPF helper functions...", + "/*** eBPF helper functions ***/", + define_prefix); + + if (define_prefix) + printf("/*\n" + " * Use %sHAVE_PROG_TYPE_HELPER(prog_type_name, helper_name)\n" + " * to determine if <helper_name> is available for <prog_type_name>,\n" + " * e.g.\n" + " * #if %sHAVE_PROG_TYPE_HELPER(xdp, bpf_redirect)\n" + " * // do stuff with this helper\n" + " * #elif\n" + " * // use a workaround\n" + " * #endif\n" + " */\n" + "#define %sHAVE_PROG_TYPE_HELPER(prog_type, helper) \\\n" + " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", + define_prefix, define_prefix, define_prefix, + define_prefix); + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_helpers_for_progtype(prog_type, prog_type_str, + supported_types[prog_type], + define_prefix, + ifindex); + } + + print_end_section(); +} + +static void section_misc(const char *define_prefix, __u32 ifindex) +{ + print_start_section("misc", + "Scanning miscellaneous eBPF features...", + "/*** eBPF misc features ***/", + define_prefix); + probe_large_insn_limit(define_prefix, ifindex); + probe_bounded_loops(define_prefix, ifindex); + probe_v2_isa_extension(define_prefix, ifindex); + probe_v3_isa_extension(define_prefix, ifindex); + probe_v4_isa_extension(define_prefix, ifindex); + print_end_section(); +} + +#ifdef USE_LIBCAP +#define capability(c) { c, false, #c } +#define capability_msg(a, i) a[i].set ? "" : a[i].name, a[i].set ? "" : ", " +#endif + +static int handle_perms(void) +{ +#ifdef USE_LIBCAP + struct { + cap_value_t cap; + bool set; + char name[14]; /* strlen("CAP_SYS_ADMIN") */ + } bpf_caps[] = { + capability(CAP_SYS_ADMIN), +#ifdef CAP_BPF + capability(CAP_BPF), + capability(CAP_NET_ADMIN), + capability(CAP_PERFMON), +#endif + }; + cap_value_t cap_list[ARRAY_SIZE(bpf_caps)]; + unsigned int i, nb_bpf_caps = 0; + bool cap_sys_admin_only = true; + cap_flag_value_t val; + int res = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + p_err("failed to get capabilities for process: %s", + strerror(errno)); + return -1; + } + +#ifdef CAP_BPF + if (CAP_IS_SUPPORTED(CAP_BPF)) + cap_sys_admin_only = false; +#endif + + for (i = 0; i < ARRAY_SIZE(bpf_caps); i++) { + const char *cap_name = bpf_caps[i].name; + cap_value_t cap = bpf_caps[i].cap; + + if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val)) { + p_err("bug: failed to retrieve %s status: %s", cap_name, + strerror(errno)); + goto exit_free; + } + + if (val == CAP_SET) { + bpf_caps[i].set = true; + cap_list[nb_bpf_caps++] = cap; + } + + if (cap_sys_admin_only) + /* System does not know about CAP_BPF, meaning that + * CAP_SYS_ADMIN is the only capability required. We + * just checked it, break. + */ + break; + } + + if ((run_as_unprivileged && !nb_bpf_caps) || + (!run_as_unprivileged && nb_bpf_caps == ARRAY_SIZE(bpf_caps)) || + (!run_as_unprivileged && cap_sys_admin_only && nb_bpf_caps)) { + /* We are all good, exit now */ + res = 0; + goto exit_free; + } + + if (!run_as_unprivileged) { + if (cap_sys_admin_only) + p_err("missing %s, required for full feature probing; run as root or use 'unprivileged'", + bpf_caps[0].name); + else + p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", + capability_msg(bpf_caps, 0), +#ifdef CAP_BPF + capability_msg(bpf_caps, 1), + capability_msg(bpf_caps, 2), + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); + goto exit_free; + } + + /* if (run_as_unprivileged && nb_bpf_caps > 0), drop capabilities. */ + if (cap_set_flag(caps, CAP_EFFECTIVE, nb_bpf_caps, cap_list, + CAP_CLEAR)) { + p_err("bug: failed to clear capabilities: %s", strerror(errno)); + goto exit_free; + } + + if (cap_set_proc(caps)) { + p_err("failed to drop capabilities: %s", strerror(errno)); + goto exit_free; + } + + res = 0; + +exit_free: + if (cap_free(caps) && !res) { + p_err("failed to clear storage object for capabilities: %s", + strerror(errno)); + res = -1; + } + + return res; +#else + /* Detection assumes user has specific privileges. + * We do not use libcap so let's approximate, and restrict usage to + * root user only. + */ + if (geteuid()) { + p_err("full feature probing requires root privileges"); + return -1; + } + + return 0; +#endif /* USE_LIBCAP */ +} + +static int do_probe(int argc, char **argv) +{ + enum probe_component target = COMPONENT_UNSPEC; + const char *define_prefix = NULL; + bool supported_types[128] = {}; + __u32 ifindex = 0; + char *ifname; + + set_max_rlimit(); + + while (argc) { + if (is_prefix(*argv, "kernel")) { + if (target != COMPONENT_UNSPEC) { + p_err("component to probe already specified"); + return -1; + } + target = COMPONENT_KERNEL; + NEXT_ARG(); + } else if (is_prefix(*argv, "dev")) { + NEXT_ARG(); + + if (target != COMPONENT_UNSPEC || ifindex) { + p_err("component to probe already specified"); + return -1; + } + if (!REQ_ARGS(1)) + return -1; + + target = COMPONENT_DEVICE; + ifname = GET_ARG(); + ifindex = if_nametoindex(ifname); + if (!ifindex) { + p_err("unrecognized netdevice '%s': %s", ifname, + strerror(errno)); + return -1; + } + } else if (is_prefix(*argv, "full")) { + full_mode = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "macros") && !define_prefix) { + define_prefix = ""; + NEXT_ARG(); + } else if (is_prefix(*argv, "prefix")) { + if (!define_prefix) { + p_err("'prefix' argument can only be use after 'macros'"); + return -1; + } + if (strcmp(define_prefix, "")) { + p_err("'prefix' already defined"); + return -1; + } + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + define_prefix = GET_ARG(); + } else if (is_prefix(*argv, "unprivileged")) { +#ifdef USE_LIBCAP + run_as_unprivileged = true; + NEXT_ARG(); +#else + p_err("unprivileged run not supported, recompile bpftool with libcap"); + return -1; +#endif + } else { + p_err("expected no more arguments, 'kernel', 'dev', 'macros' or 'prefix', got: '%s'?", + *argv); + return -1; + } + } + + /* Full feature detection requires specific privileges. + * Let's approximate, and warn if user is not root. + */ + if (handle_perms()) + return -1; + + if (json_output) { + define_prefix = NULL; + jsonw_start_object(json_wtr); + } + + section_system_config(target, define_prefix); + if (!section_syscall_config(define_prefix)) + /* bpf() syscall unavailable, don't probe other BPF features */ + goto exit_close_json; + section_program_types(supported_types, define_prefix, ifindex); + section_map_types(define_prefix, ifindex); + section_helpers(supported_types, define_prefix, ifindex); + section_misc(define_prefix, ifindex); + +exit_close_json: + if (json_output) + /* End root object */ + jsonw_end_object(json_wtr); + + return 0; +} + +static const char *get_helper_name(unsigned int id) +{ + if (id >= ARRAY_SIZE(helper_name)) + return NULL; + + return helper_name[id]; +} + +static int do_list_builtins(int argc, char **argv) +{ + const char *(*get_name)(unsigned int id); + unsigned int id = 0; + + if (argc < 1) + usage(); + + if (is_prefix(*argv, "prog_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_prog_type_str; + } else if (is_prefix(*argv, "map_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_map_type_str; + } else if (is_prefix(*argv, "attach_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_attach_type_str; + } else if (is_prefix(*argv, "link_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_link_type_str; + } else if (is_prefix(*argv, "helpers")) { + get_name = get_helper_name; + } else { + p_err("expected 'prog_types', 'map_types', 'attach_types', 'link_types' or 'helpers', got: %s", *argv); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + const char *name; + + name = get_name(id++); + if (!name) + break; + if (json_output) + jsonw_string(json_wtr, name); + else + printf("%s\n", name); + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s list_builtins GROUP\n" + " %1$s %2$s help\n" + "\n" + " COMPONENT := { kernel | dev NAME }\n" + " GROUP := { prog_types | map_types | attach_types | link_types | helpers }\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "probe", do_probe }, + { "list_builtins", do_list_builtins }, + { "help", do_help }, + { 0 } +}; + +int do_feature(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000..6ae7262eb --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,2697 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <libgen.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <bpf/btf.h> + +#include "json_writer.h" +#include "main.h" + +#define MAX_OBJ_NAME_LEN 64 + +static void sanitize_identifier(char *name) +{ + int i; + + for (i = 0; name[i]; i++) + if (!isalnum(name[i]) && name[i] != '_') + name[i] = '_'; +} + +static bool str_has_prefix(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} + +static bool str_has_suffix(const char *str, const char *suffix) +{ + size_t i, n1 = strlen(str), n2 = strlen(suffix); + + if (n1 < n2) + return false; + + for (i = 0; i < n2; i++) { + if (str[n1 - i - 1] != suffix[n2 - i - 1]) + return false; + } + + return true; +} + +static 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) +{ + 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, const char *suffix) +{ + int i; + + sprintf(guard, "__%s_%s__", obj_name, suffix); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz) +{ + static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + const char *name = bpf_map__name(map); + int i, n; + + if (!bpf_map__is_internal(map)) { + snprintf(buf, buf_sz, "%s", name); + return true; + } + + for (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) { + const char *sfx = sfxs[i], *p; + + p = strstr(name, sfx); + if (p) { + snprintf(buf, buf_sz, "%s", p + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; +} + +static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz) +{ + static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + int i, n; + + /* recognize hard coded LLVM section name */ + if (strcmp(sec_name, ".addr_space.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 *ctx, const char *fmt, va_list args) +{ + vprintf(fmt, args); +} + +static int codegen_datasec_def(struct bpf_object *obj, + struct btf *btf, + struct btf_dump *d, + const struct btf_type *sec, + const char *obj_name) +{ + const char *sec_name = btf__name_by_offset(btf, sec->name_off); + const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); + int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); + char var_ident[256], sec_ident[256]; + bool strip_mods = false; + + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + return 0; + + if (strcmp(sec_name, ".kconfig") != 0) + strip_mods = true; + + printf(" struct %s__%s {\n", obj_name, sec_ident); + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .field_name = var_ident, + .indent_level = 2, + .strip_mods = strip_mods, + ); + int need_off = sec_var->offset, align_off, align; + __u32 var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + if (off > need_off) { + p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", + sec_name, i, need_off, off); + return -EINVAL; + } + + align = btf__align_of(btf, var->type); + if (align <= 0) { + p_err("Failed to determine alignment of variable '%s': %d", + var_name, align); + return -EINVAL; + } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; + + align_off = (off + align - 1) / align * align; + if (align_off != need_off) { + printf("\t\tchar __pad%d[%d];\n", + pad_cnt, need_off - off); + pad_cnt++; + } + + /* sanitize variable name, e.g., for static vars inside + * a function, it's name is '<function name>.<variable name>', + * which we'll turn into a '<function name>_<variable name>' + */ + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t\t"); + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + return err; + printf(";\n"); + + off = sec_var->offset + sec_var->size; + } + printf(" } *%s;\n", sec_ident); + return 0; +} + +static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident) +{ + int n = btf__type_cnt(btf), i; + char sec_ident[256]; + + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) + return t; + } + return NULL; +} + +static bool is_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); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec; + char map_ident[256]; + int err = 0; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + 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; + + 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; + + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("__typeof__("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); + } + +out: + btf_dump__free(d); + return err; +} + +static void codegen(const char *template, ...) +{ + const char *src, *end; + int skip_tabs = 0, n; + char *s, *dst; + va_list args; + char c; + + n = strlen(template); + s = malloc(n + 1); + if (!s) + exit(-1); + src = template; + dst = s; + + /* find out "baseline" indentation to skip */ + while ((c = *src++)) { + if (c == '\t') { + skip_tabs++; + } else if (c == '\n') { + break; + } else { + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); + free(s); + exit(-1); + } + } + + while (*src) { + /* skip baseline indentation tabs */ + for (n = skip_tabs; n > 0; n--, src++) { + if (*src != '\t') { + p_err("not enough tabs at pos %td in template '%s'", + src - template - 1, template); + free(s); + exit(-1); + } + } + /* trim trailing whitespace */ + end = strchrnul(src, '\n'); + for (n = end - src; n > 0 && isspace(src[n - 1]); n--) + ; + memcpy(dst, src, n); + dst += n; + if (*end) + *dst++ = '\n'; + src = *end ? end + 1 : end; + } + *dst++ = '\0'; + + /* print out using adjusted template */ + va_start(args, template); + n = vprintf(s, args); + va_end(args); + + free(s); +} + +static void print_hex(const char *data, int data_sz) +{ + int i, len; + + for (i = 0, len = 0; i < data_sz; i++) { + int w = data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)data[i]); + } +} + +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map); + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ +static void codegen_asserts(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct bpf_map *map; + struct btf_var_secinfo *sec_var; + int i, vlen; + const struct btf_type *sec; + char map_ident[256], var_ident[256]; + + if (!btf) + return; + + codegen("\ + \n\ + __attribute__((unused)) static void \n\ + %1$s__assert(struct %1$s *s __attribute__((unused))) \n\ + { \n\ + #ifdef __cplusplus \n\ + #define _Static_assert static_assert \n\ + #endif \n\ + ", obj_name); + + bpf_object__for_each_map(map, obj) { + if (!is_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$zu);\n", + ident, bpf_map_mmap_sz(map)); + codegen("\ + \n\ + skel_closenz(skel->maps.%1$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_load_and_run_opts sopts = {}; + char sig_buf[MAX_SIG_SIZE]; + __u8 prog_sha[SHA256_DIGEST_LENGTH]; + struct bpf_map *map; + + char ident[256]; + int err = 0; + + if (sign_progs) + opts.gen_hash = true; + + 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$s *skel; \n\ + \n\ + skel = (struct %1$s *)skel_alloc(sizeof(*skel)); \n\ + if (!skel) \n\ + goto cleanup; \n\ + skel->ctx.sz = (char *)&skel->links - (char *)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$s = (__typeof__(skel->%1$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$s *skel) \n\ + { \n\ + struct bpf_load_and_run_opts opts = {}; \n\ + int err; \n\ + static const char opts_data[] __attribute__((__aligned__(8))) = \"\\\n\ + ", + obj_name); + print_hex(opts.data, opts.data_sz); + codegen("\ + \n\ + \"; \n\ + static const char opts_insn[] __attribute__((__aligned__(8))) = \"\\\n\ + "); + print_hex(opts.insns, opts.insns_sz); + codegen("\ + \n\ + \";\n"); + + if (sign_progs) { + sopts.insns = opts.insns; + sopts.insns_sz = opts.insns_sz; + sopts.excl_prog_hash = prog_sha; + sopts.excl_prog_hash_sz = sizeof(prog_sha); + sopts.signature = sig_buf; + sopts.signature_sz = MAX_SIG_SIZE; + + err = bpftool_prog_sign(&sopts); + if (err < 0) { + p_err("failed to sign program"); + goto out; + } + + codegen("\ + \n\ + static const char opts_sig[] __attribute__((__aligned__(8))) = \"\\\n\ + "); + print_hex((const void *)sig_buf, sopts.signature_sz); + codegen("\ + \n\ + \";\n"); + + codegen("\ + \n\ + static const char opts_excl_hash[] __attribute__((__aligned__(8))) = \"\\\n\ + "); + print_hex((const void *)prog_sha, sizeof(prog_sha)); + codegen("\ + \n\ + \";\n"); + + codegen("\ + \n\ + opts.signature = (void *)opts_sig; \n\ + opts.signature_sz = sizeof(opts_sig) - 1; \n\ + opts.excl_prog_hash = (void *)opts_excl_hash; \n\ + opts.excl_prog_hash_sz = sizeof(opts_excl_hash) - 1; \n\ + opts.keyring_id = skel->keyring_id; \n\ + "); + } + + codegen("\ + \n\ + opts.ctx = (struct bpf_loader_ctx *)skel; \n\ + opts.data_sz = sizeof(opts_data) - 1; \n\ + opts.data = (void *)opts_data; \n\ + opts.insns_sz = sizeof(opts_insn) - 1; \n\ + opts.insns = (void *)opts_insn; \n\ + \n\ + err = bpf_load_and_run(&opts); \n\ + if (err < 0) \n\ + return err; \n\ + "); + bpf_object__for_each_map(map, obj) { + const char *mmap_flags; + + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) + mmap_flags = "PROT_READ"; + else + mmap_flags = "PROT_READ | PROT_WRITE"; + + codegen("\ + \n\ + skel->%1$s = (__typeof__(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, bool populate_links) +{ + struct bpf_map *map; + char ident[256]; + size_t i, map_sz; + + if (!map_cnt) + return; + + /* for backward compatibility with old libbpf versions that don't + * handle new BPF skeleton with new struct bpf_map_skeleton definition + * that includes link field, avoid specifying new increased size, + * unless we absolutely have to (i.e., if there are struct_ops maps + * present) + */ + map_sz = offsetof(struct bpf_map_skeleton, link); + if (populate_links) { + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) { + map_sz = sizeof(struct bpf_map_skeleton); + break; + } + } + } + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = %zu; \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt,\n\ + sizeof(*s->maps) > %zu ? sizeof(*s->maps) : %zu);\n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + map_cnt, map_sz, map_sz, map_sz + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + map = (struct bpf_map_skeleton *)((char *)s->maps + %zu * s->map_skel_sz);\n\ + map->name = \"%s\"; \n\ + map->map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), ident); + /* memory-mapped internal maps */ + if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) { + printf("\tmap->mmaped = (void **)&obj->%s;\n", ident); + } + + if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) { + codegen("\ + \n\ + map->link = &obj->links.%s; \n\ + ", 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[%u];\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[%u];\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$s = (__typeof__(obj->struct_ops.%1$s))\n\ + 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 map_cnt = 0, prog_cnt = 0, attach_map_cnt = 0, file_sz, mmap_sz; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file; + char ident[256]; + struct bpf_program *prog; + int fd, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + opts.object_name = obj_name; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + 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_obj; + } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) { + p_err("ignoring unrecognized internal map '%s'...", + bpf_map__name(map)); + continue; + } + + if (bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) + attach_map_cnt++; + + map_cnt++; + } + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + get_header_guard(header_guard, obj_name, "SKEL_H"); + if (use_loader) { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <bpf/skel_internal.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_loader_ctx ctx; \n\ + ", + obj_name, header_guard + ); + } else { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + #define BPF_SKEL_SUPPORTS_MAP_AUTO_ATTACH 1 \n\ + \n\ + struct %1$s { \n\ + struct bpf_object_skeleton *skeleton; \n\ + struct bpf_object *obj; \n\ + ", + obj_name, header_guard + ); + } + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (use_loader) + printf("\t\tstruct bpf_map_desc %s;\n", ident); + else + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + btf = bpf_object__btf(obj); + err = gen_st_ops_shadow(obj_name, btf, obj); + if (err) + goto out; + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + if (use_loader) + printf("\t\tstruct bpf_prog_desc %s;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + if (prog_cnt + attach_map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + if (use_loader) + printf("\t\tint %s_fd;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); + } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + + if (use_loader) + printf("\t\tint %s_fd;\n", ident); + else + printf("\t\tstruct bpf_link *%s;\n", ident); + } + + printf("\t} links;\n"); + } + + if (sign_progs) { + codegen("\ + \n\ + __s32 keyring_id; \n\ + "); + } + + if (btf) { + err = codegen_datasecs(obj, obj_name); + if (err) + goto out; + } + if (use_loader) { + err = gen_trace(obj, obj_name, header_guard); + goto out; + } + + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\ + static inline struct %1$s *open_and_load(); \n\ + static inline int load(struct %1$s *skel); \n\ + static inline int attach(struct %1$s *skel); \n\ + static inline void detach(struct %1$s *skel); \n\ + static inline void destroy(struct %1$s *skel); \n\ + static inline const void *elf_bytes(size_t *sz); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *obj) \n\ + { \n\ + if (!obj) \n\ + return; \n\ + if (obj->skeleton) \n\ + bpf_object__destroy_skeleton(obj->skeleton);\n\ + free(obj); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj); \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ + { \n\ + struct %1$s *obj; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ + return NULL; \n\ + } \n\ + \n\ + err = %1$s__create_skeleton(obj); \n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + ", obj_name); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ + return obj; \n\ + err_out: \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + return %1$s__open_opts(NULL); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *obj) \n\ + { \n\ + return bpf_object__load_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *obj; \n\ + int err; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + err = %1$s__load(obj); \n\ + if (err) { \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + return obj; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__attach_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *obj) \n\ + { \n\ + bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + struct bpf_map_skeleton *map __attribute__((unused));\n\ + int err; \n\ + \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/, true /*links*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + + codegen("\ + \n\ + \n\ + 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 + ); + + /* embed contents of BPF object file */ + print_hex(obj_data, file_sz); + + codegen("\ + \n\ + \"; \n\ + \n\ + *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); +out_obj: + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + 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\ + #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$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + struct bpf_map_skeleton *map __attribute__((unused));\n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + obj_name, var_cnt + ); + + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; + } + } + + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/, false /*links*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + + codegen("\ + \n\ + \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + "); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ + ", + obj_name, header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_object(int argc, char **argv) +{ + struct bpf_linker *linker; + const char *output_file, *file; + int err = 0; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + output_file = GET_ARG(); + + linker = bpf_linker__new(output_file, NULL); + if (!linker) { + p_err("failed to create BPF linker instance"); + return -1; + } + + while (argc) { + file = GET_ARG(); + + err = bpf_linker__add_file(linker, file, NULL); + if (err) { + p_err("failed to link '%s': %s (%d)", file, strerror(errno), errno); + goto out; + } + } + + err = bpf_linker__finalize(linker); + if (err) { + p_err("failed to finalize ELF file: %s (%d)", strerror(errno), errno); + goto out; + } + + err = 0; +out: + bpf_linker__free(linker); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" + " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-L|--use-loader} | [ {-S|--sign } {-k} <private_key.pem> {-i} <certificate.x509> ]}\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; + __u32 i; + int err; + + 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 (%u)", 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 (%u)", + 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 err; + __u32 i; + + 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); + __u32 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: { + __u32 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 (%u)", 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; +} + +/* 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 n = btf__type_cnt(info->marked_btf); + int err = 0; + __u32 i; + + 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; + __u32 vlen, 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); + struct btf_field_iter it; + __u32 *type_id; + + err = btf_field_iter_init(&it, btf_type, BTF_FIELD_ITER_IDS); + if (err) + goto err_out; + + while ((type_id = btf_field_iter_next(&it))) + *type_id = ids[*type_id]; + } + + free(ids); + return btf_new; + +err_out: + btf__free(btf_new); + free(ids); + errno = -err; + return NULL; +} + +/* Create minimized BTF file for a set of BPF objects. + * + * The BTFGen algorithm is divided in two main parts: (1) collect the + * BTF types that are involved in relocations and (2) generate the BTF + * object using the collected types. + * + * In order to collect the types involved in the relocations, we parse + * the BTF and BTF.ext sections of the BPF objects and use + * bpf_core_calc_relo_insn() to get the target specification, this + * indicates how the types and fields are used in a relocation. + * + * Types are recorded in different ways according to the kind of the + * relocation. For field-based relocations only the members that are + * actually used are saved in order to reduce the size of the generated + * BTF file. For type-based relocations empty struct / unions are + * generated and for enum-based relocations the whole type is saved. + * + * The second part of the algorithm generates the BTF object. It creates + * an empty BTF object and fills it with the types recorded in the + * previous step. This function takes care of only adding the structure + * and union members that were marked as used and it also fixes up the + * type IDs on the generated BTF object. + */ +static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[]) +{ + struct btfgen_info *info; + struct btf *btf_new = NULL; + int err, i; + + info = btfgen_new_info(src_btf); + if (!info) { + err = -errno; + p_err("failed to allocate info structure: %s", strerror(errno)); + goto out; + } + + for (i = 0; objspaths[i] != NULL; i++) { + err = btfgen_record_obj(info, objspaths[i]); + if (err) { + p_err("error recording relocations for %s: %s", objspaths[i], + strerror(errno)); + goto out; + } + } + + btf_new = btfgen_get_btf(info); + if (!btf_new) { + err = -errno; + p_err("error generating BTF: %s", strerror(errno)); + goto out; + } + + err = btf_save_raw(btf_new, dst_btf); + if (err) { + p_err("error saving btf file: %s", strerror(errno)); + goto out; + } + +out: + btf__free(btf_new); + btfgen_free_info(info); + + return err; +} + +static int do_min_core_btf(int argc, char **argv) +{ + const char *input, *output, **objs; + int i, err; + + if (!REQ_ARGS(3)) { + usage(); + return -1; + } + + input = GET_ARG(); + output = GET_ARG(); + + objs = (const char **) calloc(argc + 1, sizeof(*objs)); + if (!objs) { + p_err("failed to allocate array for object names"); + return -ENOMEM; + } + + i = 0; + while (argc) + objs[i++] = GET_ARG(); + + err = minimize_btf(input, output, objs); + free(objs); + return err; +} + +static const struct cmd cmds[] = { + { "object", do_object }, + { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, + { "min_core_btf", do_min_core_btf}, + { "help", do_help }, + { 0 } +}; + +int do_gen(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c new file mode 100644 index 000000000..df5f0d1e0 --- /dev/null +++ b/tools/bpf/bpftool/iter.c @@ -0,0 +1,123 @@ +// 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> + +#include "main.h" + +static int do_pin(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, iter_opts); + union bpf_iter_link_info linfo; + const char *objfile, *path; + struct bpf_program *prog; + struct bpf_object *obj; + struct bpf_link *link; + int err = -1, map_fd = -1; + + if (!REQ_ARGS(2)) + usage(); + + objfile = GET_ARG(); + path = GET_ARG(); + + /* optional arguments */ + if (argc) { + if (is_prefix(*argv, "map")) { + NEXT_ARG(); + + if (!REQ_ARGS(2)) { + p_err("incorrect map spec"); + return -1; + } + + map_fd = map_parse_fd(&argc, &argv, BPF_F_RDONLY); + 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 (!obj) { + err = -errno; + p_err("can't open objfile %s", objfile); + goto close_map_fd; + } + + err = bpf_object__load(obj); + if (err) { + p_err("can't load objfile %s", objfile); + goto close_obj; + } + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -errno; + p_err("can't find bpf program in objfile %s", objfile); + goto close_obj; + } + + 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_file(path); + if (err) + goto close_link; + + err = bpf_link__pin(link, path); + if (err) { + p_err("pin_iter failed for program %s to path %s", + bpf_program__name(prog), path); + goto close_link; + } + +close_link: + bpf_link__destroy(link); +close_obj: + bpf_object__close(obj); +close_map_fd: + if (map_fd >= 0) + close(map_fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %1$s %2$s pin OBJ PATH [map MAP]\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, "iter"); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "pin", do_pin }, + { 0 } +}; + +int do_iter(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c new file mode 100644 index 000000000..04541155e --- /dev/null +++ b/tools/bpf/bpftool/jit_disasm.c @@ -0,0 +1,431 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Based on: + * + * Minimal BPF JIT image disassembler + * + * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for + * debugging or verification purposes. + * + * Copyright 2013 Daniel Borkmann <daniel@iogearbox.net> + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdio.h> +#include <stdarg.h> +#include <stdint.h> +#include <stdlib.h> +#include <unistd.h> +#include <string.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 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, + __maybe_unused __u64 func_ksym) +{ + char *triple; + + if (arch) + triple = LLVMNormalizeTargetTriple(arch); + else + triple = LLVMGetDefaultTargetTriple(); + if (!triple) { + p_err("Failed to retrieve triple"); + return -1; + } + + /* + * Enable all aarch64 ISA extensions so the disassembler can handle any + * instruction the kernel JIT might emit (e.g. ARM64 LSE atomics). + */ + if (!strncmp(triple, "aarch64", 7)) + *ctx = LLVMCreateDisasmCPUFeatures(triple, "", "+all", NULL, 0, NULL, + symbol_lookup_callback); + else + *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, + __u64 func_ksym) +{ + char buf[256]; + int count; + + count = LLVMDisasmInstruction(*ctx, image + pc, len - pc, func_ksym + 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" + +struct disasm_info { + struct disassemble_info info; + __u64 func_ksym; +}; + +static void disasm_print_addr(bfd_vma addr, struct disassemble_info *info) +{ + struct disasm_info *dinfo = container_of(info, struct disasm_info, info); + + addr += dinfo->func_ksym; + generic_print_address(addr, info); +} + +typedef struct { + struct disasm_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); + if (len <= 0) + return -1; + + tpath[len] = 0; + + return 0; +} + +static int printf_json(void *out, const char *fmt, va_list ap) +{ + char *s; + int err; + + err = vasprintf(&s, fmt, ap); + if (err < 0) + return -1; + + if (!oper_count) { + int i; + + /* Strip trailing spaces */ + i = strlen(s) - 1; + while (s[i] == ' ') + s[i--] = '\0'; + + jsonw_string_field(json_wtr, "operation", s); + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count++; + } else if (!strcmp(fmt, ",")) { + /* Skip */ + } else { + jsonw_string(json_wtr, s); + oper_count++; + } + free(s); + return 0; +} + +static int fprintf_json(void *out, const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int init_context(disasm_ctx_t *ctx, const char *arch, + const char *disassembler_options, + unsigned char *image, ssize_t len, __u64 func_ksym) +{ + struct disassemble_info *info; + char tpath[PATH_MAX]; + bfd *bfdf; + + memset(tpath, 0, 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; + + ctx->info = malloc(sizeof(struct disasm_info)); + if (!ctx->info) { + p_err("mem alloc failed"); + goto err_close; + } + ctx->info->func_ksym = func_ksym; + info = &ctx->info->info; + + if (json_output) + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); + else + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); + + /* Update architecture info for offload. */ + if (arch) { + const bfd_arch_info_type *inf = bfd_scan_arch(arch); + + if (inf) { + bfdf->arch_info = inf; + } else { + p_err("No libbfd support for %s", arch); + goto err_free; + } + } + + 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->print_address_func = disasm_print_addr; + + disassemble_init_for_target(info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + ctx->disassemble = disassembler(info->arch, + bfd_big_endian(bfdf), + info->mach, + bfdf); +#else + ctx->disassemble = disassembler(bfdf); +#endif + 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, + __maybe_unused __u64 func_ksym) +{ + return ctx->disassemble(pc, &ctx->info->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; + unsigned int pc = 0; + disasm_ctx_t ctx; + + if (!len) + return -1; + + if (init_context(&ctx, arch, disassembler_options, image, len, func_ksym)) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + do { + if (prog_linfo) { + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + func_ksym + pc, + func_idx, + nr_skip); + if (linfo) + nr_skip++; + } + + if (json_output) { + jsonw_start_object(json_wtr); + oper_count = 0; + if (linfo) + btf_dump_linfo_json(btf, linfo, linum); + jsonw_name(json_wtr, "pc"); + jsonw_printf(json_wtr, "\"0x%x\"", pc); + } else { + if (linfo) + btf_dump_linfo_plain(btf, linfo, "; ", + linum); + printf("%4x:" DISASM_SPACER, pc); + } + + count = disassemble_insn(&ctx, image, len, pc, func_ksym); + + if (json_output) { + /* Operand array, was started in fprintf_json. Before + * that, make sure we have a _null_ value if no operand + * other than operation code was present. + */ + if (oper_count == 1) + jsonw_null(json_wtr); + jsonw_end_array(json_wtr); + } + + if (opcodes) { + if (json_output) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_array(json_wtr); + for (i = 0; i < count; ++i) + jsonw_printf(json_wtr, "\"0x%02hhx\"", + (uint8_t)image[pc + i]); + jsonw_end_array(json_wtr); + } else { + printf("\n\t"); + for (i = 0; i < count; ++i) + printf("%02x ", + (uint8_t)image[pc + i]); + } + } + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + pc += count; + } while (count > 0 && pc < len); + if (json_output) + jsonw_end_array(json_wtr); + + destroy_context(&ctx); + + return 0; +} diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c new file mode 100644 index 000000000..be379613d --- /dev/null +++ b/tools/bpf/bpftool/json_writer.c @@ -0,0 +1,355 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause) +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> +#include <assert.h> +#include <malloc.h> +#include <inttypes.h> +#include <stdint.h> + +#include "json_writer.h" + +struct json_writer { + FILE *out; /* output file */ + unsigned depth; /* nesting */ + bool pretty; /* optional whitepace */ + char sep; /* either nul or comma */ +}; + +/* indentation for pretty print */ +static void jsonw_indent(json_writer_t *self) +{ + unsigned i; + for (i = 0; i < self->depth; ++i) + fputs(" ", self->out); +} + +/* end current line and indent if pretty printing */ +static void jsonw_eol(json_writer_t *self) +{ + if (!self->pretty) + return; + + putc('\n', self->out); + jsonw_indent(self); +} + +/* If current object is not empty print a comma */ +static void jsonw_eor(json_writer_t *self) +{ + if (self->sep != '\0') + putc(self->sep, self->out); + self->sep = ','; +} + + +/* Output JSON encoded string */ +/* Handles C escapes, does not do Unicode */ +static void jsonw_puts(json_writer_t *self, const char *str) +{ + putc('"', self->out); + for (; *str; ++str) + switch (*str) { + case '\t': + fputs("\\t", self->out); + break; + case '\n': + fputs("\\n", self->out); + break; + case '\r': + fputs("\\r", self->out); + break; + case '\f': + fputs("\\f", self->out); + break; + case '\b': + fputs("\\b", self->out); + break; + case '\\': + fputs("\\\\", self->out); + break; + case '"': + fputs("\\\"", self->out); + break; + default: + putc(*str, self->out); + } + putc('"', self->out); +} + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f) +{ + json_writer_t *self = malloc(sizeof(*self)); + if (self) { + self->out = f; + self->depth = 0; + self->pretty = false; + self->sep = '\0'; + } + return self; +} + +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p) +{ + json_writer_t *self = *self_p; + + assert(self->depth == 0); + fputs("\n", self->out); + fflush(self->out); + free(self); + *self_p = NULL; +} + +void jsonw_pretty(json_writer_t *self, bool on) +{ + self->pretty = on; +} + +void jsonw_reset(json_writer_t *self) +{ + assert(self->depth == 0); + self->sep = '\0'; +} + +/* Basic blocks */ +static void jsonw_begin(json_writer_t *self, int c) +{ + jsonw_eor(self); + putc(c, self->out); + ++self->depth; + self->sep = '\0'; +} + +static void jsonw_end(json_writer_t *self, int c) +{ + assert(self->depth > 0); + + --self->depth; + if (self->sep != '\0') + jsonw_eol(self); + putc(c, self->out); + self->sep = ','; +} + + +/* Add a JSON property name */ +void jsonw_name(json_writer_t *self, const char *name) +{ + jsonw_eor(self); + jsonw_eol(self); + self->sep = '\0'; + jsonw_puts(self, name); + putc(':', self->out); + if (self->pretty) + putc(' ', self->out); +} + +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +{ + jsonw_eor(self); + putc('"', self->out); + vfprintf(self->out, fmt, ap); + putc('"', self->out); +} + +void jsonw_printf(json_writer_t *self, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + jsonw_eor(self); + vfprintf(self->out, fmt, ap); + va_end(ap); +} + +/* Collections */ +void jsonw_start_object(json_writer_t *self) +{ + jsonw_begin(self, '{'); +} + +void jsonw_end_object(json_writer_t *self) +{ + jsonw_end(self, '}'); +} + +void jsonw_start_array(json_writer_t *self) +{ + jsonw_begin(self, '['); +} + +void jsonw_end_array(json_writer_t *self) +{ + jsonw_end(self, ']'); +} + +/* JSON value types */ +void jsonw_string(json_writer_t *self, const char *value) +{ + jsonw_eor(self); + jsonw_puts(self, value); +} + +void jsonw_bool(json_writer_t *self, bool val) +{ + jsonw_printf(self, "%s", val ? "true" : "false"); +} + +void jsonw_null(json_writer_t *self) +{ + jsonw_printf(self, "null"); +} + +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num) +{ + jsonw_printf(self, fmt, num); +} + +#ifdef notused +void jsonw_float(json_writer_t *self, double num) +{ + jsonw_printf(self, "%g", num); +} +#endif + +void jsonw_hu(json_writer_t *self, unsigned short num) +{ + jsonw_printf(self, "%hu", num); +} + +void jsonw_uint(json_writer_t *self, uint64_t num) +{ + jsonw_printf(self, "%"PRIu64, num); +} + +void jsonw_lluint(json_writer_t *self, unsigned long long int num) +{ + jsonw_printf(self, "%llu", num); +} + +void jsonw_int(json_writer_t *self, int64_t num) +{ + jsonw_printf(self, "%"PRId64, num); +} + +/* Basic name/value objects */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val) +{ + jsonw_name(self, prop); + jsonw_string(self, val); +} + +void jsonw_bool_field(json_writer_t *self, const char *prop, bool val) +{ + jsonw_name(self, prop); + jsonw_bool(self, val); +} + +#ifdef notused +void jsonw_float_field(json_writer_t *self, const char *prop, double val) +{ + jsonw_name(self, prop); + jsonw_float(self, val); +} +#endif + +void jsonw_float_field_fmt(json_writer_t *self, + const char *prop, + const char *fmt, + double val) +{ + jsonw_name(self, prop); + jsonw_float_fmt(self, fmt, val); +} + +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num) +{ + jsonw_name(self, prop); + jsonw_uint(self, num); +} + +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num) +{ + jsonw_name(self, prop); + jsonw_hu(self, num); +} + +void jsonw_lluint_field(json_writer_t *self, + const char *prop, + unsigned long long int num) +{ + jsonw_name(self, prop); + jsonw_lluint(self, num); +} + +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num) +{ + jsonw_name(self, prop); + jsonw_int(self, num); +} + +void jsonw_null_field(json_writer_t *self, const char *prop) +{ + jsonw_name(self, prop); + jsonw_null(self); +} + +#ifdef TEST +int main(int argc, char **argv) +{ + json_writer_t *wr = jsonw_new(stdout); + + jsonw_start_object(wr); + jsonw_pretty(wr, true); + jsonw_name(wr, "Vyatta"); + jsonw_start_object(wr); + jsonw_string_field(wr, "url", "http://vyatta.com"); + jsonw_uint_field(wr, "downloads", 2000000ul); + jsonw_float_field(wr, "stock", 8.16); + + jsonw_name(wr, "ARGV"); + jsonw_start_array(wr); + while (--argc) + jsonw_string(wr, *++argv); + jsonw_end_array(wr); + + jsonw_name(wr, "empty"); + jsonw_start_array(wr); + jsonw_end_array(wr); + + jsonw_name(wr, "NIL"); + jsonw_start_object(wr); + jsonw_end_object(wr); + + jsonw_null_field(wr, "my_null"); + + jsonw_name(wr, "special chars"); + jsonw_start_array(wr); + jsonw_string_field(wr, "slash", "/"); + jsonw_string_field(wr, "newline", "\n"); + jsonw_string_field(wr, "tab", "\t"); + jsonw_string_field(wr, "ff", "\f"); + jsonw_string_field(wr, "quote", "\""); + jsonw_string_field(wr, "tick", "\'"); + jsonw_string_field(wr, "backslash", "\\"); + jsonw_end_array(wr); + + jsonw_end_object(wr); + + jsonw_end_object(wr); + jsonw_destroy(&wr); + return 0; +} + +#endif diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h new file mode 100644 index 000000000..5aaffd3b8 --- /dev/null +++ b/tools/bpf/bpftool/json_writer.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#ifndef _JSON_WRITER_H_ +#define _JSON_WRITER_H_ + +#include <stdbool.h> +#include <stdint.h> +#include <stdarg.h> +#include <stdio.h> +#include <linux/compiler.h> + +/* Opaque class structure */ +typedef struct json_writer json_writer_t; + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f); +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p); + +/* Cause output to have pretty whitespace */ +void jsonw_pretty(json_writer_t *self, bool on); + +/* Reset separator to create new JSON */ +void jsonw_reset(json_writer_t *self); + +/* Add property name */ +void jsonw_name(json_writer_t *self, const char *name); + +/* Add value */ +void __printf(2, 0) jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, + va_list ap); +void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...); +void jsonw_string(json_writer_t *self, const char *value); +void jsonw_bool(json_writer_t *self, bool value); +void jsonw_float(json_writer_t *self, double number); +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num); +void jsonw_uint(json_writer_t *self, uint64_t number); +void jsonw_hu(json_writer_t *self, unsigned short number); +void jsonw_int(json_writer_t *self, int64_t number); +void jsonw_null(json_writer_t *self); +void jsonw_lluint(json_writer_t *self, unsigned long long int num); + +/* Useful Combinations of name and value */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val); +void jsonw_bool_field(json_writer_t *self, const char *prop, bool value); +void jsonw_float_field(json_writer_t *self, const char *prop, double num); +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num); +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num); +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num); +void jsonw_null_field(json_writer_t *self, const char *prop); +void jsonw_lluint_field(json_writer_t *self, const char *prop, + unsigned long long int num); +void jsonw_float_field_fmt(json_writer_t *self, const char *prop, + const char *fmt, double val); + +/* Collections */ +void jsonw_start_object(json_writer_t *self); +void jsonw_end_object(json_writer_t *self); + +void jsonw_start_array(json_writer_t *self); +void jsonw_end_array(json_writer_t *self); + +/* Override default exception handling */ +typedef void (jsonw_err_handler_fn)(const char *); + +#endif /* _JSON_WRITER_H_ */ diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c new file mode 100644 index 000000000..bdcd717b0 --- /dev/null +++ b/tools/bpf/bpftool/link.c @@ -0,0 +1,1298 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* 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" + +#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; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) + p_err("failed to get link with ID %u: %s", id, strerror(errno)); + return fd; + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_LINK, NULL); + } + + p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + return -1; +} + +static void +show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + const char *link_type_str; + + jsonw_uint_field(wtr, "id", info->id); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + jsonw_string_field(wtr, "type", link_type_str); + else + jsonw_uint_field(wtr, "type", info->type); + + jsonw_uint_field(json_wtr, "prog_id", info->prog_id); +} + +static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) +{ + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + jsonw_string_field(wtr, "attach_type", attach_type_str); + else + jsonw_uint_field(wtr, "attach_type", attach_type); +} + +static 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); + int err, prog_fd; + + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + return prog_fd; + + memset(info, 0, sizeof(*info)); + err = bpf_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 bool is_x86_ibt_enabled(void) +{ +#if defined(__x86_64__) + struct kernel_config_option options[] = { + { "CONFIG_X86_KERNEL_IBT", }, + }; + char *values[ARRAY_SIZE(options)] = { }; + bool ret; + + if (read_kernel_config(options, ARRAY_SIZE(options), values, NULL)) + return false; + + ret = !!values[0]; + free(values[0]); + return ret; +#else + return false; +#endif +} + +static bool +symbol_matches_target(__u64 sym_addr, __u64 target_addr, bool is_ibt_enabled) +{ + if (sym_addr == target_addr) + return true; + + /* + * On x86_64 architectures with CET (Control-flow Enforcement Technology), + * function entry points have a 4-byte 'endbr' instruction prefix. + * This causes kprobe hooks to target the address *after* 'endbr' + * (symbol address + 4), preserving the CET instruction. + * Here we check if the symbol address matches the hook target address + * minus 4, indicating a CET-enabled function entry point. + */ + if (is_ibt_enabled && sym_addr == target_addr - 4) + return true; + + return false; +} + +static void +show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + struct addr_cookie *data; + __u32 i, j = 0; + bool is_ibt_enabled; + + 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; + + is_ibt_enabled = is_x86_ibt_enabled(); + for (i = 0; i < dd.sym_count; i++) { + if (!symbol_matches_target(dd.sym_mapping[i].address, + data[j].addr, is_ibt_enabled)) + continue; + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "addr", (unsigned long)data[j].addr); + 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); + jsonw_uint_field(wtr, "ref_ctr_offset", info->perf_event.uprobe.ref_ctr_offset); +} + +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, "%llu-", 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), + "%llu-", (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), + "%llu", 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); + + show_link_header_json(info, json_wtr); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "tp_name", + u64_to_ptr(info->raw_tracepoint.tp_name)); + jsonw_uint_field(json_wtr, "cookie", info->raw_tracepoint.cookie); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + jsonw_string_field(json_wtr, "prog_type", prog_type_str); + else + jsonw_uint_field(json_wtr, "prog_type", prog_info.type); + + show_link_attach_type_json(info->tracing.attach_type, + json_wtr); + 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); + jsonw_uint_field(json_wtr, "cookie", info->tracing.cookie); + 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_SOCKMAP: + jsonw_uint_field(json_wtr, "map_id", info->sockmap.map_id); + show_link_attach_type_json(info->sockmap.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 (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(link_table, entry, 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; +} + +static void show_link_header_plain(struct bpf_link_info *info) +{ + const char *link_type_str; + + printf("%u: ", info->id); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + printf("%s ", link_type_str); + else + printf("type %u ", info->type); + + 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) +{ + 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(%u)", + 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: %u", 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; + bool is_ibt_enabled; + + 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; + + is_ibt_enabled = is_x86_ibt_enabled(); + printf("\n\t%-16s %-16s %s", "addr", "cookie", "func [module]"); + for (i = 0; i < dd.sym_count; i++) { + if (!symbol_matches_target(dd.sym_mapping[i].address, + data[j].addr, is_ibt_enabled)) + continue; + printf("\n\t%016lx %-16llx %s", + (unsigned long)data[j].addr, 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 %u ", 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); + if (info->perf_event.uprobe.ref_ctr_offset) + printf("ref_ctr_offset 0x%llx ", info->perf_event.uprobe.ref_ctr_offset); +} + +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); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + printf("\n\ttp '%s' ", + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); + if (info->raw_tracepoint.cookie) + printf("cookie %llu ", info->raw_tracepoint.cookie); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + printf("\n\tprog_type %s ", prog_type_str); + else + printf("\n\tprog_type %u ", prog_info.type); + + show_link_attach_type_plain(info->tracing.attach_type); + 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); + if (info->tracing.cookie) + printf("\n\tcookie %llu ", info->tracing.cookie); + 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_SOCKMAP: + printf("\n\t"); + printf("map_id %u ", info->sockmap.map_id); + show_link_attach_type_plain(info->sockmap.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 (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; + + 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"); + + return 0; +} + +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 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_link_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get link info: %s", + strerror(errno)); + close(fd); + return err; + } + if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && + !info.raw_tracepoint.tp_name) { + info.raw_tracepoint.tp_name = 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; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err, fd; + + if (show_pinned) { + link_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(link_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(link_table, BPF_OBJ_LINK); + } + build_obj_refs_table(&refs_table, BPF_OBJ_LINK); + + if (argc == 2) { + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return fd; + do_show_link(fd); + goto out; + } + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get link by id (%u): %s", + id, strerror(errno)); + break; + } + + err = do_show_link(fd); + if (err) + break; + } + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(link_table); + +out: + if (dd.sym_count) + kernel_syms_destroy(&dd); + return errno == ENOENT ? 0 : -1; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, link_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_detach(int argc, char **argv) +{ + int err, fd; + + if (argc != 2) { + p_err("link specifier is invalid or missing\n"); + return 1; + } + + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return 1; + + err = bpf_link_detach(fd); + if (err) + err = -errno; + close(fd); + if (err) { + p_err("failed link detach: %s", strerror(-err)); + return 1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [LINK]\n" + " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s detach LINK\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_LINK "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "pin", do_pin }, + { "detach", do_detach }, + { 0 } +}; + +int do_link(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c new file mode 100644 index 000000000..c91e1a6e1 --- /dev/null +++ b/tools/bpf/bpftool/main.c @@ -0,0 +1,579 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#include <ctype.h> +#include <errno.h> +#include <getopt.h> +#include <linux/bpf.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> + +#include "main.h" + +#define BATCH_LINE_LEN_MAX 65536 +#define BATCH_ARG_NB_MAX 4096 + +const char *bin_name; +static int last_argc; +static char **last_argv; +static int (*last_do_help)(int argc, char **argv); +json_writer_t *json_wtr; +bool pretty_output; +bool json_output; +bool show_pinned; +bool block_mount; +bool verifier_logs; +bool relaxed_maps; +bool use_loader; +struct btf *base_btf; +struct hashmap *refs_table; +bool sign_progs; +const char *private_key_path; +const char *cert_path; + +static void __noreturn clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + +void usage(void) +{ + last_do_help(last_argc - 1, last_argv + 1); + + clean_and_exit(-1); +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n" + " %s batch file FILE\n" + " %s version\n" + "\n" + " OBJECT := { prog | map | link | cgroup | perf | net | feature | btf | gen | struct_ops | iter | token }\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 }, + { "token", do_token }, + { "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 +#ifdef BPFTOOL_WITHOUT_CRYPTO + const bool has_crypto = false; +#else + const bool has_crypto = 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); /* root object */ + + jsonw_name(json_wtr, "version"); +#ifdef BPFTOOL_VERSION + jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION); +#else + jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + jsonw_name(json_wtr, "libbpf_version"); + jsonw_printf(json_wtr, "\"%u.%u\"", + 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, "crypto", has_crypto); + 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("crypto", has_crypto, &nb_features); + print_feature("skeletons", has_skeletons, &nb_features); + print_feature("bootstrap", bootstrap, &nb_features); + printf("\n"); + } + return 0; +} + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)) +{ + unsigned int i; + + last_argc = argc; + last_argv = argv; + last_do_help = help; + + if (argc < 1 && cmds[0].func) + return cmds[0].func(argc, argv); + + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not supported in bootstrap mode", + cmds[i].cmd); + return -1; + } + return cmds[i].func(argc - 1, argv + 1); + } + } + + help(argc - 1, argv + 1); + + return -1; +} + +bool is_prefix(const char *pfx, const char *str) +{ + if (!pfx) + return false; + if (strlen(str) < strlen(pfx)) + return false; + + return !memcmp(str, pfx, strlen(pfx)); +} + +/* Last argument MUST be NULL pointer */ +int detect_common_prefix(const char *arg, ...) +{ + unsigned int count = 0; + const char *ref; + char msg[256]; + va_list ap; + + snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg); + va_start(ap, arg); + while ((ref = va_arg(ap, const char *))) { + if (!is_prefix(arg, ref)) + continue; + count++; + if (count > 1) + strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1); + strncat(msg, ref, sizeof(msg) - strlen(msg) - 1); + } + va_end(ap); + strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); + + if (count >= 2) { + p_err("%s", msg); + return -1; + } + + return 0; +} + +void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep) +{ + unsigned char *data = arg; + unsigned int i; + + for (i = 0; i < n; i++) { + const char *pfx = ""; + + if (!i) + /* nothing */; + else if (!(i % 16)) + fprintf(f, "\n"); + else if (!(i % 8)) + fprintf(f, " "); + else + pfx = sep; + + fprintf(f, "%s%02hhx", i ? pfx : "", data[i]); + } +} + +/* Split command line into argument vector. */ +static int make_args(char *line, char *n_argv[], int maxargs, int cmd_nb) +{ + static const char ws[] = " \t\r\n"; + char *cp = line; + int n_argc = 0; + + while (*cp) { + /* Skip leading whitespace. */ + cp += strspn(cp, ws); + + if (*cp == '\0') + break; + + if (n_argc >= (maxargs - 1)) { + p_err("too many arguments to command %d", cmd_nb); + return -1; + } + + /* Word begins with quote. */ + if (*cp == '\'' || *cp == '"') { + char quote = *cp++; + + n_argv[n_argc++] = cp; + /* Find ending quote. */ + cp = strchr(cp, quote); + if (!cp) { + p_err("unterminated quoted string in command %d", + cmd_nb); + return -1; + } + } else { + n_argv[n_argc++] = cp; + + /* Find end of word. */ + cp += strcspn(cp, ws); + if (*cp == '\0') + break; + } + + /* Separate words. */ + *cp++ = 0; + } + n_argv[n_argc] = NULL; + + return n_argc; +} + +static int do_batch(int argc, char **argv) +{ + char buf[BATCH_LINE_LEN_MAX], contline[BATCH_LINE_LEN_MAX]; + char *n_argv[BATCH_ARG_NB_MAX]; + unsigned int lines = 0; + int n_argc; + FILE *fp; + char *cp; + int err = 0; + int i; + + if (argc < 2) { + p_err("too few parameters for batch"); + return -1; + } else if (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(); + + if (!strcmp(*argv, "-")) + fp = stdin; + else + fp = fopen(*argv, "r"); + if (!fp) { + p_err("Can't open file (%s): %s", *argv, strerror(errno)); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); + while (fgets(buf, sizeof(buf), fp)) { + cp = strchr(buf, '#'); + if (cp) + *cp = '\0'; + + if (strlen(buf) == sizeof(buf) - 1) { + errno = E2BIG; + break; + } + + /* Append continuation lines if any (coming after a line ending + * with '\' in the batch file). + */ + while ((cp = strstr(buf, "\\\n")) != NULL) { + if (!fgets(contline, sizeof(contline), fp) || + strlen(contline) == 0) { + p_err("missing continuation line on command %u", + lines); + err = -1; + goto err_close; + } + + cp = strchr(contline, '#'); + if (cp) + *cp = '\0'; + + if (strlen(buf) + strlen(contline) + 1 > sizeof(buf)) { + p_err("command %u is too long", lines); + err = -1; + goto err_close; + } + buf[strlen(buf) - 2] = '\0'; + strcat(buf, contline); + } + + n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines); + if (!n_argc) + continue; + if (n_argc < 0) { + err = n_argc; + goto err_close; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "command"); + jsonw_start_array(json_wtr); + for (i = 0; i < n_argc; i++) + jsonw_string(json_wtr, n_argv[i]); + jsonw_end_array(json_wtr); + jsonw_name(json_wtr, "output"); + } + + err = cmd_select(commands, n_argc, n_argv, do_help); + + if (json_output) + jsonw_end_object(json_wtr); + + if (err) + goto err_close; + + lines++; + } + + if (errno && errno != ENOENT) { + p_err("reading batch file failed: %s", strerror(errno)); + err = -1; + } else { + if (!json_output) + printf("processed %u commands\n", lines); + } +err_close: + if (fp != stdin) + fclose(fp); + + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +int main(int argc, char **argv) +{ + static const struct option options[] = { + { "json", no_argument, NULL, 'j' }, + { "help", no_argument, NULL, 'h' }, + { "pretty", no_argument, NULL, 'p' }, + { "version", no_argument, NULL, 'V' }, + { "bpffs", no_argument, NULL, 'f' }, + { "mapcompat", no_argument, NULL, 'm' }, + { "nomount", no_argument, NULL, 'n' }, + { "debug", no_argument, NULL, 'd' }, + { "use-loader", no_argument, NULL, 'L' }, + { "sign", no_argument, NULL, 'S' }, + { "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 = "bpftool"; + + opterr = 0; + while ((opt = getopt_long(argc, argv, "VhpjfLmndSi:k:B:l", + options, NULL)) >= 0) { + switch (opt) { + case 'V': + version_requested = true; + break; + case 'h': + return do_help(argc, argv); + case 'p': + pretty_output = true; + /* fall through */ + case 'j': + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); + break; + case 'f': + show_pinned = true; + break; + case 'm': + relaxed_maps = true; + break; + case 'n': + block_mount = true; + break; + case 'd': + libbpf_set_print(print_all_levels); + verifier_logs = true; + break; + case 'B': + base_btf = btf__parse(optarg, NULL); + if (!base_btf) { + p_err("failed to parse base BTF at '%s': %d\n", + optarg, -errno); + return -1; + } + break; + case 'L': + use_loader = true; + break; + case 'S': + sign_progs = true; + use_loader = true; + break; + case 'k': + private_key_path = optarg; + break; + case 'i': + cert_path = optarg; + break; + default: + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); + } + } + + argc -= optind; + argv += optind; + if (argc < 0) + usage(); + + if (sign_progs && (private_key_path == NULL || cert_path == NULL)) { + p_err("-i <identity_x509_cert> and -k <private_key> must be supplied with -S for signing"); + return -EINVAL; + } + + if (!sign_progs && (private_key_path != NULL || cert_path != NULL)) { + p_err("--sign (or -S) must be explicitly passed with -i <identity_x509_cert> and -k <private_key> to sign the programs"); + return -EINVAL; + } + + if (version_requested) + ret = do_version(argc, argv); + else + ret = cmd_select(commands, argc, argv, do_help); + + if (json_output) + jsonw_destroy(&json_wtr); + + btf__free(base_btf); + + return ret; +} diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h new file mode 100644 index 000000000..78b6e0ebb --- /dev/null +++ b/tools/bpf/bpftool/main.h @@ -0,0 +1,312 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_H +#define __BPF_TOOL_H + +/* BFD and kernel.h both define GCC_VERSION, differently */ +#undef GCC_VERSION +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdbool.h> +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <bpf/skel_internal.h> +#include <linux/bpf.h> +#include <linux/compiler.h> +#include <linux/kernel.h> + +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> + +#include "json_writer.h" + +/* Make sure we do not use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} + +#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) +#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) +#define GET_ARG() ({ argc--; *argv++; }) +#define REQ_ARGS(cnt) \ + ({ \ + int _cnt = (cnt); \ + bool _res; \ + \ + if (argc < _cnt) { \ + p_err("'%s' needs at least %d arguments, %d found", \ + argv[-1], _cnt, argc); \ + _res = false; \ + } else { \ + _res = true; \ + } \ + _res; \ + }) + +#define ERR_MAX_LEN 1024 +#define MAX_SIG_SIZE 4096 + +#define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" + +#define HELP_SPEC_PROGRAM \ + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" +#define HELP_SPEC_OPTIONS \ + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug}" +#define HELP_SPEC_MAP \ + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" +#define HELP_SPEC_LINK \ + "LINK := { id LINK_ID | pinned FILE }" + +/* keep in sync with the definition in skeleton/pid_iter.bpf.c */ +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, + BPF_OBJ_LINK, + BPF_OBJ_BTF, +}; + +extern const char *bin_name; + +extern json_writer_t *json_wtr; +extern bool json_output; +extern bool show_pinned; +extern bool show_pids; +extern bool block_mount; +extern bool verifier_logs; +extern bool relaxed_maps; +extern bool use_loader; +extern struct btf *base_btf; +extern struct hashmap *refs_table; +extern bool sign_progs; +extern const char *private_key_path; +extern const char *cert_path; + +void __printf(1, 2) p_err(const char *fmt, ...); +void __printf(1, 2) p_info(const char *fmt, ...); + +bool is_prefix(const char *pfx, const char *str); +int detect_common_prefix(const char *arg, ...); +void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); +void usage(void) __noreturn; + +void set_max_rlimit(void); + +int mount_tracefs(const char *target); + +struct obj_ref { + int pid; + char comm[16]; +}; + +struct obj_refs { + int ref_cnt; + bool has_bpf_cookie; + struct obj_ref *refs; + __u64 bpf_cookie; +}; + +struct btf; +struct bpf_line_info; + +int build_pinned_obj_table(struct hashmap *table, + enum bpf_obj_type type); +void delete_pinned_obj_table(struct hashmap *table); +__weak int build_obj_refs_table(struct hashmap **table, + enum bpf_obj_type type); +__weak void delete_obj_refs_table(struct hashmap *table); +__weak void emit_obj_refs_json(struct hashmap *table, __u32 id, + json_writer_t *json_wtr); +__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id, + const char *prefix); +void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); +void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); + +struct cmd { + const char *cmd; + int (*func)(int argc, char **argv); +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)); + +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + +int get_fd_type(int fd); +const char *get_fd_type_name(enum bpf_obj_type type); +char *get_fdinfo(int fd, const char *key); +int open_obj_pinned(const char *path, bool quiet, + const struct bpf_obj_get_opts *opts); +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type, + const struct bpf_obj_get_opts *opts); +int mount_bpffs_for_file(const char *file_name); +int create_and_mount_bpffs_dir(const char *dir_name); +int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); +int do_pin_fd(int fd, const char *name); + +/* commands available in bootstrap mode */ +int do_gen(int argc, char **argv); +int do_btf(int argc, char **argv); + +/* non-bootstrap only commands */ +int do_prog(int argc, char **arg) __weak; +int do_map(int argc, char **arg) __weak; +int do_link(int argc, char **arg) __weak; +int do_event_pipe(int argc, char **argv) __weak; +int do_cgroup(int argc, char **arg) __weak; +int do_perf(int argc, char **arg) __weak; +int do_net(int argc, char **arg) __weak; +int do_tracelog(int argc, char **arg) __weak; +int do_feature(int argc, char **argv) __weak; +int do_struct_ops(int argc, char **argv) __weak; +int do_iter(int argc, char **argv) __weak; +int do_token(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, __u32 open_flags); +int map_parse_fds(int *argc, char ***argv, int **fds, __u32 open_flags); +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len, __u32 open_flags); + +struct bpf_prog_linfo; +#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 +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 JIT disassembly support"); + return -1; +} +#endif +void print_data_json(uint8_t *data, size_t len); +void print_hex_data_json(uint8_t *data, size_t len); + +unsigned int get_page_size(void); +unsigned int get_possible_cpus(void); +const char * +ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt); + +struct btf_dumper { + const struct btf *btf; + json_writer_t *jw; + bool is_plain_text; + bool prog_id_as_func_ptr; +}; + +/* btf_dumper_type - print data along with type information + * @d: an instance containing context for dumping types + * @type_id: index in btf->types array. this points to the type to be dumped + * @data: pointer the actual data, i.e. the values to be printed + * + * Returns zero on success and negative error code otherwise + */ +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data); +void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id, + char *func_only, int size); + +void btf_dump_linfo_plain(const struct btf *btf, + const struct bpf_line_info *linfo, + const char *prefix, bool linum); +void btf_dump_linfo_json(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum); +void btf_dump_linfo_dotlabel(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum); + +struct nlattr; +struct ifinfomsg; +struct tcmsg; +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb); +int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, + const char *devname, int ifindex); + +int print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args); + +size_t hash_fn_for_key_as_id(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); + +struct kernel_config_option { + const char *name; + bool macro_dump; +}; + +int read_kernel_config(const struct kernel_config_option *requested_options, + size_t num_options, char **out_values, + const char *define_prefix); +#ifndef BPFTOOL_WITHOUT_CRYPTO +int bpftool_prog_sign(struct bpf_load_and_run_opts *opts); +__u32 register_session_key(const char *key_der_path); +#else +static inline int bpftool_prog_sign(struct bpf_load_and_run_opts *opts) +{ + p_err("bpftool was built without signing support"); + return -ENOTSUP; +} + +static inline __u32 register_session_key(const char *key_der_path) +{ + p_err("bpftool was built without signing support"); + return -1; +} +#endif +#endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c new file mode 100644 index 000000000..71a45d966 --- /dev/null +++ b/tools/bpf/bpftool/map.c @@ -0,0 +1,1514 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <net/if.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> + +#include "json_writer.h" +#include "main.h" + +static struct hashmap *map_table; + +static bool map_is_per_cpu(__u32 type) +{ + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; +} + +static bool map_is_map_of_maps(__u32 type) +{ + return type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS; +} + +static bool map_is_map_of_progs(__u32 type) +{ + return type == BPF_MAP_TYPE_PROG_ARRAY; +} + +static int map_type_from_str(const char *type) +{ + const char *map_type_str; + unsigned int i; + + for (i = 0; ; i++) { + map_type_str = libbpf_bpf_map_type_str(i); + if (!map_type_str) + break; + + /* Don't allow prefixing in case of possible future shadowing */ + if (!strcmp(map_type_str, type)) + return i; + } + return -1; +} + +static void *alloc_value(struct bpf_map_info *info) +{ + if (map_is_per_cpu(info->type)) + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); + else + return malloc(info->value_size); +} + +static int do_dump_btf(const struct btf_dumper *d, + struct bpf_map_info *map_info, void *key, + void *value) +{ + __u32 value_id; + int ret = 0; + + /* start of key-value pair */ + jsonw_start_object(d->jw); + + if (map_info->btf_key_type_id) { + jsonw_name(d->jw, "key"); + + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + } + + value_id = map_info->btf_vmlinux_value_type_id ? + : map_info->btf_value_type_id; + + if (!map_is_per_cpu(map_info->type)) { + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, value_id, value); + } else { + unsigned int i, n, step; + + jsonw_name(d->jw, "values"); + jsonw_start_array(d->jw); + n = get_possible_cpus(); + step = round_up(map_info->value_size, 8); + for (i = 0; i < n; i++) { + jsonw_start_object(d->jw); + jsonw_int_field(d->jw, "cpu", i); + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, value_id, value + i * step); + jsonw_end_object(d->jw); + if (ret) + break; + } + jsonw_end_array(d->jw); + } + +err_end_obj: + /* end of key-value pair */ + jsonw_end_object(d->jw); + + return ret; +} + +static json_writer_t *get_btf_writer(void) +{ + json_writer_t *jw = jsonw_new(stdout); + + if (!jw) + return NULL; + jsonw_pretty(jw, true); + + return jw; +} + +static void print_entry_json(struct bpf_map_info *info, unsigned char *key, + unsigned char *value, struct btf *btf) +{ + jsonw_start_object(json_wtr); + + if (!map_is_per_cpu(info->type)) { + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info->key_size); + jsonw_name(json_wtr, "value"); + print_hex_data_json(value, info->value_size); + if (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, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } + } else { + unsigned int i, n, step; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info->key_size); + + jsonw_name(json_wtr, "values"); + jsonw_start_array(json_wtr); + for (i = 0; i < n; i++) { + jsonw_start_object(json_wtr); + + jsonw_int_field(json_wtr, "cpu", i); + + jsonw_name(json_wtr, "value"); + print_hex_data_json(value + i * step, + info->value_size); + + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } + } + + jsonw_end_object(json_wtr); +} + +static void +print_entry_error_msg(struct bpf_map_info *info, unsigned char *key, + const char *error_msg) +{ + int msg_size = strlen(error_msg); + bool single_line, break_names; + + break_names = info->key_size > 16 || msg_size > 16; + single_line = info->key_size + msg_size <= 24 && !break_names; + + printf("key:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, key, info->key_size, " "); + + printf(single_line ? " " : "\n"); + + printf("value:%c%s", break_names ? '\n' : ' ', error_msg); + + printf("\n"); +} + +static void +print_entry_error(struct bpf_map_info *map_info, void *key, int lookup_errno) +{ + /* For prog_array maps or arrays of maps, failure to lookup the value + * means there is no entry for that key. Do not print an error message + * in that case. + */ + if ((map_is_map_of_maps(map_info->type) || + map_is_map_of_progs(map_info->type)) && lookup_errno == ENOENT) + return; + + if (json_output) { + jsonw_start_object(json_wtr); /* entry */ + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, map_info->key_size); + jsonw_name(json_wtr, "value"); + jsonw_start_object(json_wtr); /* error */ + jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); + jsonw_end_object(json_wtr); /* error */ + jsonw_end_object(json_wtr); /* entry */ + } else { + const char *msg = NULL; + + if (lookup_errno == ENOENT) + msg = "<no entry>"; + else if (lookup_errno == ENOSPC && + map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + msg = "<cannot read>"; + + print_entry_error_msg(map_info, key, + msg ? : strerror(lookup_errno)); + } +} + +static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, + unsigned char *value) +{ + if (!map_is_per_cpu(info->type)) { + bool single_line, break_names; + + break_names = info->key_size > 16 || info->value_size > 16; + single_line = info->key_size + info->value_size <= 24 && + !break_names; + + if (info->key_size) { + printf("key:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, key, info->key_size, " "); + + printf(single_line ? " " : "\n"); + } + + if (info->value_size) { + 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"); + } else { + unsigned int i, n, step; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + + if (info->key_size) { + printf("key:\n"); + fprint_hex(stdout, key, info->key_size, " "); + printf("\n"); + } + if (info->value_size) { + for (i = 0; i < n; i++) { + printf("value (CPU %02u):%c", + i, info->value_size > 16 ? '\n' : ' '); + fprint_hex(stdout, value + i * step, + info->value_size, " "); + printf("\n"); + } + } + } +} + +static char **parse_bytes(char **argv, const char *name, unsigned char *val, + unsigned int n) +{ + unsigned int i = 0, base = 0; + char *endptr; + + if (is_prefix(*argv, "hex")) { + base = 16; + argv++; + } + + while (i < n && argv[i]) { + val[i] = strtoul(argv[i], &endptr, base); + if (*endptr) { + p_err("error parsing byte: %s", argv[i]); + return NULL; + } + i++; + } + + if (i != n) { + p_err("%s expected %u bytes got %u", name, n, i); + return NULL; + } + + return argv + i; +} + +/* on per cpu maps we must copy the provided value on all value instances */ +static void fill_per_cpu_value(struct bpf_map_info *info, void *value) +{ + unsigned int i, n, step; + + if (!map_is_per_cpu(info->type)) + return; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + for (i = 1; i < n; i++) + memcpy(value + i * step, value, info->value_size); +} + +static int parse_elem(char **argv, struct bpf_map_info *info, void *key, + void *value, __u32 key_size, __u32 value_size, + __u32 *flags, __u32 **value_fd, __u32 open_flags) +{ + if (!*argv) { + if (!key && !value) + return 0; + p_err("did not find %s", key ? "key" : "value"); + return -1; + } + + if (is_prefix(*argv, "key")) { + if (!key) { + if (key_size) + p_err("duplicate key"); + else + p_err("unnecessary key"); + return -1; + } + + argv = parse_bytes(argv + 1, "key", key, key_size); + if (!argv) + return -1; + + return parse_elem(argv, info, NULL, value, key_size, value_size, + flags, value_fd, open_flags); + } else if (is_prefix(*argv, "value")) { + int fd; + + if (!value) { + if (value_size) + p_err("duplicate value"); + else + p_err("unnecessary value"); + return -1; + } + + argv++; + + if (map_is_map_of_maps(info->type)) { + int argc = 2; + + if (value_size != 4) { + p_err("value smaller than 4B for map in map?"); + return -1; + } + if (!argv[0] || !argv[1]) { + p_err("not enough value arguments for map in map"); + return -1; + } + + fd = map_parse_fd(&argc, &argv, open_flags); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else if (map_is_map_of_progs(info->type)) { + int argc = 2; + + if (value_size != 4) { + p_err("value smaller than 4B for map of progs?"); + return -1; + } + if (!argv[0] || !argv[1]) { + p_err("not enough value arguments for map of progs"); + return -1; + } + if (is_prefix(*argv, "id")) + p_info("Warning: updating program array via MAP_ID, make sure this map is kept open\n" + " by some process or pinned otherwise update will be lost"); + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else { + argv = parse_bytes(argv, "value", value, value_size); + if (!argv) + return -1; + + fill_per_cpu_value(info, value); + } + + return parse_elem(argv, info, key, NULL, key_size, value_size, + flags, NULL, open_flags); + } else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") || + is_prefix(*argv, "exist")) { + if (!flags) { + p_err("flags specified multiple times: %s", *argv); + return -1; + } + + if (is_prefix(*argv, "any")) + *flags = BPF_ANY; + else if (is_prefix(*argv, "noexist")) + *flags = BPF_NOEXIST; + else if (is_prefix(*argv, "exist")) + *flags = BPF_EXIST; + + return parse_elem(argv + 1, info, key, value, key_size, + value_size, NULL, value_fd, open_flags); + } + + p_err("expected key or value, got: %s", *argv); + return -1; +} + +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + const char *map_type_str; + + jsonw_uint_field(wtr, "id", info->id); + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + jsonw_string_field(wtr, "type", map_type_str); + else + jsonw_uint_field(wtr, "type", info->type); + + if (*info->name) + jsonw_string_field(wtr, "name", info->name); + + jsonw_name(wtr, "flags"); + jsonw_printf(wtr, "%u", info->map_flags); +} + +static int show_map_close_json(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + jsonw_start_object(json_wtr); + + show_map_header_json(info, json_wtr); + + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); + + jsonw_uint_field(json_wtr, "bytes_key", info->key_size); + jsonw_uint_field(json_wtr, "bytes_value", info->value_size); + jsonw_uint_field(json_wtr, "max_entries", info->max_entries); + + if (memlock) + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); + free(memlock); + + if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { + char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); + char *owner_jited = get_fdinfo(fd, "owner_jited"); + + if (owner_prog_type) { + unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; + + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + jsonw_string_field(json_wtr, "owner_prog_type", + prog_type_str); + else + jsonw_uint_field(json_wtr, "owner_prog_type", + prog_type); + } + if (owner_jited) + jsonw_bool_field(json_wtr, "owner_jited", + !!atoi(owner_jited)); + + free(owner_prog_type); + free(owner_jited); + } + close(fd); + + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + jsonw_int_field(json_wtr, "frozen", frozen); + + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(map_table, entry, 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; +} + +static void show_map_header_plain(struct bpf_map_info *info) +{ + const char *map_type_str; + + printf("%u: ", info->id); + + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + printf("%s ", map_type_str); + else + printf("type %u ", info->type); + + if (*info->name) + printf("name %s ", info->name); + + printf("flags 0x%x", info->map_flags); + print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("\n"); +} + +static int show_map_close_plain(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + show_map_header_plain(info); + printf("\tkey %uB value %uB max_entries %u", + info->key_size, info->value_size, info->max_entries); + + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { + char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); + char *owner_jited = get_fdinfo(fd, "owner_jited"); + + if (owner_prog_type || owner_jited) + printf("\n\t"); + if (owner_prog_type) { + unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; + + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + printf("owner_prog_type %s ", prog_type_str); + else + printf("owner_prog_type %u ", prog_type); + } + if (owner_jited) + printf("owner%s jited", + atoi(owner_jited) ? "" : " not"); + + free(owner_prog_type); + free(owner_jited); + } + close(fd); + + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; + + hashmap__for_each_key_entry(map_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); + } + + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + + if (info->btf_id || frozen) + printf("\n\t"); + + if (info->btf_id) + printf("btf_id %u", info->btf_id); + + if (frozen) + printf("%sfrozen", info->btf_id ? " " : ""); + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); + return 0; +} + +static int do_show_subset(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = bpf_map_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", + strerror(errno)); + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + + if (json_output) + show_map_close_json(fds[i], &info); + else + show_map_close_plain(fds[i], &info); + + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + +static int do_show(int argc, char **argv) +{ + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 id = 0; + int err; + int fd; + + opts.open_flags = BPF_F_RDONLY; + + if (show_pinned) { + map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(map_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(map_table, BPF_OBJ_MAP); + } + build_obj_refs_table(&refs_table, BPF_OBJ_MAP); + + if (argc == 2) + return do_show_subset(argc, argv); + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next map: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_map_get_fd_by_id_opts(id, &opts); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + break; + } + + err = bpf_map_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + break; + } + + if (json_output) + show_map_close_json(fd, &info); + else + show_map_close_plain(fd, &info); + } + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(map_table); + + return errno == ENOENT ? 0 : -1; +} + +static int dump_map_elem(int fd, void *key, void *value, + struct bpf_map_info *map_info, struct btf *btf, + json_writer_t *btf_wtr) +{ + if (bpf_map_lookup_elem(fd, key, value)) { + print_entry_error(map_info, key, errno); + return -1; + } + + if (json_output) { + print_entry_json(map_info, key, value, btf); + } else if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, map_info, key, value); + } else { + print_entry_plain(map_info, key, value); + } + + return 0; +} + +static int maps_have_btf(int *fds, int nb_fds) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int err, i; + + for (i = 0; i < nb_fds; i++) { + err = bpf_map_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + return -1; + } + + if (!info.btf_id) + return 0; + } + + return 1; +} + +static struct btf *btf_vmlinux; + +static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf) +{ + int err = 0; + + if (info->btf_vmlinux_value_type_id) { + if (!btf_vmlinux) { + btf_vmlinux = libbpf_find_kernel_btf(); + if (!btf_vmlinux) { + p_err("failed to get kernel btf"); + return -errno; + } + } + *btf = btf_vmlinux; + } else if (info->btf_value_type_id) { + *btf = btf__load_from_kernel_by_id(info->btf_id); + if (!*btf) { + err = -errno; + p_err("failed to get btf"); + } + } else { + *btf = NULL; + } + + return err; +} + +static void free_map_kv_btf(struct btf *btf) +{ + if (btf != btf_vmlinux) + btf__free(btf); +} + +static int +map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, + bool show_header) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct btf *btf = NULL; + int err; + + key = malloc(info->key_size); + value = alloc_value(info); + if (!key || !value) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + prev_key = NULL; + + if (wtr) { + err = get_map_kv_btf(info, &btf); + if (err) { + goto exit_free; + } + + if (show_header) { + jsonw_start_object(wtr); /* map object */ + show_map_header_json(info, wtr); + jsonw_name(wtr, "elements"); + } + jsonw_start_array(wtr); /* elements */ + } else if (show_header) { + show_map_header_plain(info); + } + + if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info->value_size != 8) { + const char *map_type_str; + + map_type_str = libbpf_bpf_map_type_str(info->type); + p_info("Warning: cannot read values from %s map with value_size != 8", + map_type_str); + } + while (true) { + err = bpf_map_get_next_key(fd, prev_key, key); + if (err) { + if (errno == ENOENT) + err = 0; + break; + } + if (!dump_map_elem(fd, key, value, info, btf, wtr)) + num_elems++; + prev_key = key; + } + + if (wtr) { + jsonw_end_array(wtr); /* elements */ + if (show_header) + jsonw_end_object(wtr); /* map object */ + } else { + printf("Found %u element%s\n", num_elems, + num_elems != 1 ? "s" : ""); + } + +exit_free: + free(key); + free(value); + close(fd); + free_map_kv_btf(btf); + + return err; +} + +static int do_dump(int argc, char **argv) +{ + json_writer_t *wtr = NULL, *btf_wtr = NULL; + struct bpf_map_info info = {}; + int nb_fds, i = 0; + __u32 len = sizeof(info); + int *fds = NULL; + int err = -1; + + if (argc != 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY); + if (nb_fds < 1) + goto exit_free; + + if (json_output) { + wtr = json_wtr; + } else { + int do_plain_btf; + + do_plain_btf = maps_have_btf(fds, nb_fds); + if (do_plain_btf < 0) + goto exit_close; + + if (do_plain_btf) { + btf_wtr = get_btf_writer(); + wtr = btf_wtr; + if (!btf_wtr) + p_info("failed to create json writer for btf. falling back to plain output"); + } + } + + if (wtr && nb_fds > 1) + jsonw_start_array(wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + if (bpf_map_get_info_by_fd(fds[i], &info, &len)) { + p_err("can't get map info: %s", strerror(errno)); + break; + } + err = map_dump(fds[i], &info, wtr, nb_fds > 1); + if (!wtr && i != nb_fds - 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (wtr && nb_fds > 1) + jsonw_end_array(wtr); /* root array */ + + if (btf_wtr) + jsonw_destroy(&btf_wtr); +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + btf__free(btf_vmlinux); + return err; +} + +static int alloc_key_value(struct bpf_map_info *info, void **key, void **value) +{ + *key = NULL; + *value = NULL; + + if (info->key_size) { + *key = malloc(info->key_size); + if (!*key) { + p_err("key mem alloc failed"); + return -1; + } + } + + if (info->value_size) { + *value = alloc_value(info); + if (!*value) { + p_err("value mem alloc failed"); + free(*key); + *key = NULL; + return -1; + } + } + + return 0; +} + +static int do_update(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 *value_fd = NULL; + __u32 flags = BPF_ANY; + void *key, *value; + int fd, err; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = parse_elem(argv, &info, key, value, info.key_size, + info.value_size, &flags, &value_fd, 0); + if (err) + goto exit_free; + + err = bpf_map_update_elem(fd, key, value, flags); + if (err) { + p_err("update failed: %s", strerror(errno)); + goto exit_free; + } + +exit_free: + if (value_fd) + close(*value_fd); + free(key); + free(value); + close(fd); + + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static void print_key_value(struct bpf_map_info *info, void *key, + void *value) +{ + json_writer_t *btf_wtr; + struct btf *btf; + + if (get_map_kv_btf(info, &btf)) + return; + + if (json_output) { + print_entry_json(info, key, value, btf); + } else if (btf) { + /* if here json_wtr wouldn't have been initialised, + * so let's create separate writer for btf + */ + btf_wtr = get_btf_writer(); + if (!btf_wtr) { + p_info("failed to create json writer for btf. falling back to plain output"); + btf__free(btf); + btf = NULL; + print_entry_plain(info, key, value); + } else { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, info, key, value); + jsonw_destroy(&btf_wtr); + } + } else { + print_entry_plain(info, key, value); + } + btf__free(btf); +} + +static int do_lookup(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *value; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL, + BPF_F_RDONLY); + if (err) + goto exit_free; + + err = bpf_map_lookup_elem(fd, key, value); + if (err) { + if (errno == ENOENT) { + if (json_output) { + jsonw_null(json_wtr); + } else { + printf("key:\n"); + fprint_hex(stdout, key, info.key_size, " "); + printf("\n\nNot found\n"); + } + } else { + p_err("lookup failed: %s", strerror(errno)); + } + + goto exit_free; + } + + /* here means bpf_map_lookup_elem() succeeded */ + print_key_value(&info, key, value); + +exit_free: + free(key); + free(value); + close(fd); + + return err; +} + +static int do_getnext(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *nextkey; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + nextkey = malloc(info.key_size); + if (!key || !nextkey) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + if (argc) { + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, + NULL, BPF_F_RDONLY); + if (err) + goto exit_free; + } else { + free(key); + key = NULL; + } + + err = bpf_map_get_next_key(fd, key, nextkey); + if (err) { + p_err("can't get next key: %s", strerror(errno)); + goto exit_free; + } + + if (json_output) { + jsonw_start_object(json_wtr); + if (key) { + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info.key_size); + } else { + jsonw_null_field(json_wtr, "key"); + } + jsonw_name(json_wtr, "next_key"); + print_hex_data_json(nextkey, info.key_size); + jsonw_end_object(json_wtr); + } else { + if (key) { + printf("key:\n"); + fprint_hex(stdout, key, info.key_size, " "); + printf("\n"); + } else { + printf("key: None\n"); + } + printf("next key:\n"); + fprint_hex(stdout, nextkey, info.key_size, " "); + printf("\n"); + } + +exit_free: + free(nextkey); + free(key); + close(fd); + + return err; +} + +static int do_delete(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + if (!key) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL, + 0); + if (err) + goto exit_free; + + err = bpf_map_delete_elem(fd, key); + if (err) + p_err("delete failed: %s", strerror(errno)); + +exit_free: + free(key); + close(fd); + + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int map_parse_read_only_fd(int *argc, char ***argv) +{ + return map_parse_fd(argc, argv, BPF_F_RDONLY); +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, map_parse_read_only_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_create(int argc, char **argv) +{ + LIBBPF_OPTS(bpf_map_create_opts, attr); + enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC; + __u32 key_size = 0, value_size = 0, max_entries = 0; + const char *map_name = NULL; + const char *pinfile; + int err = -1, fd; + + if (!REQ_ARGS(7)) + return -1; + pinfile = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "type")) { + NEXT_ARG(); + + if (map_type) { + p_err("map type already specified"); + goto exit; + } + + map_type = map_type_from_str(*argv); + if ((int)map_type < 0) { + p_err("unrecognized map type: %s", *argv); + goto exit; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "name")) { + NEXT_ARG(); + map_name = GET_ARG(); + if (strlen(map_name) > BPF_OBJ_NAME_LEN - 1) { + p_info("Warning: map name is longer than %u characters, it will be truncated.", + BPF_OBJ_NAME_LEN - 1); + } + } else if (is_prefix(*argv, "key")) { + if (parse_u32_arg(&argc, &argv, &key_size, + "key size")) + goto exit; + } else if (is_prefix(*argv, "value")) { + if (parse_u32_arg(&argc, &argv, &value_size, + "value size")) + goto exit; + } else if (is_prefix(*argv, "entries")) { + if (parse_u32_arg(&argc, &argv, &max_entries, + "max entries")) + goto exit; + } else if (is_prefix(*argv, "flags")) { + if (parse_u32_arg(&argc, &argv, &attr.map_flags, + "flags")) + goto exit; + } else if (is_prefix(*argv, "dev")) { + 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"); + goto exit; + } + + attr.map_ifindex = if_nametoindex(*argv); + if (!attr.map_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto exit; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "inner_map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int inner_map_fd; + + NEXT_ARG(); + if (!REQ_ARGS(2)) + usage(); + inner_map_fd = map_parse_fd_and_info(&argc, &argv, + &info, &len, BPF_F_RDONLY); + if (inner_map_fd < 0) + return -1; + attr.inner_map_fd = inner_map_fd; + } else { + p_err("unknown arg %s", *argv); + goto exit; + } + } + + if (!map_name) { + p_err("map name not specified"); + goto exit; + } + + set_max_rlimit(); + + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); + if (fd < 0) { + p_err("map create failed: %s", strerror(errno)); + goto exit; + } + + err = do_pin_fd(fd, pinfile); + close(fd); + if (err) + goto exit; + + if (json_output) + jsonw_null(json_wtr); + +exit: + if (attr.inner_map_fd > 0) + close(attr.inner_map_fd); + + return err; +} + +static int do_pop_dequeue(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *value; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = bpf_map_lookup_and_delete_elem(fd, key, value); + if (err) { + if (errno == ENOENT) { + if (json_output) + jsonw_null(json_wtr); + else + printf("Error: empty map\n"); + } else { + p_err("pop failed: %s", strerror(errno)); + } + + goto exit_free; + } + + print_key_value(&info, key, value); + +exit_free: + free(key); + free(value); + close(fd); + + return err; +} + +static int do_freeze(int argc, char **argv) +{ + int err, fd; + + if (!REQ_ARGS(2)) + return -1; + + fd = map_parse_fd(&argc, &argv, 0); + if (fd < 0) + return -1; + + if (argc) { + close(fd); + return BAD_ARG(); + } + + err = bpf_map_freeze(fd); + close(fd); + if (err) { + p_err("failed to freeze map: %s", strerror(errno)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [MAP]\n" + " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" + " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" + " [inner_map MAP] [offload_dev NAME]\n" + " %1$s %2$s dump MAP\n" + " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" + " %1$s %2$s lookup MAP [key DATA]\n" + " %1$s %2$s getnext MAP [key DATA]\n" + " %1$s %2$s delete MAP key DATA\n" + " %1$s %2$s pin MAP FILE\n" + " %1$s %2$s event_pipe MAP [cpu N index M]\n" + " %1$s %2$s peek MAP\n" + " %1$s %2$s push MAP value VALUE\n" + " %1$s %2$s pop MAP\n" + " %1$s %2$s enqueue MAP value VALUE\n" + " %1$s %2$s dequeue MAP\n" + " %1$s %2$s freeze MAP\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " DATA := { [hex] BYTES }\n" + " " HELP_SPEC_PROGRAM "\n" + " VALUE := { DATA | MAP | PROG }\n" + " UPDATE_FLAGS := { any | exist | noexist }\n" + " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" + " percpu_array | stack_trace | cgroup_array | lru_hash |\n" + " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" + " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" + " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" + " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" + " task_storage | bloom_filter | user_ringbuf | cgrp_storage | arena |\n" + " insn_array | rhash }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { "update", do_update }, + { "lookup", do_lookup }, + { "getnext", do_getnext }, + { "delete", do_delete }, + { "pin", do_pin }, + { "event_pipe", do_event_pipe }, + { "create", do_create }, + { "peek", do_lookup }, + { "push", do_update }, + { "enqueue", do_update }, + { "pop", do_pop_dequeue }, + { "dequeue", do_pop_dequeue }, + { "freeze", do_freeze }, + { 0 } +}; + +int do_map(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 000000000..bcb767e2d --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ +/* This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <errno.h> +#include <fcntl.h> +#include <bpf/libbpf.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> + +#include <bpf/bpf.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static volatile bool stop; + +struct perf_event_sample { + struct perf_event_header header; + __u64 time; + __u32 size; + unsigned char data[]; +}; + +struct perf_event_lost { + struct perf_event_header header; + __u64 id; + __u64 lost; +}; + +static void int_exit(int signo) +{ + fprintf(stderr, "Stopping...\n"); + stop = true; +} + +struct event_pipe_ctx { + bool all_cpus; + int cpu; + int idx; +}; + +static enum bpf_perf_event_ret +print_bpf_output(void *private_data, int cpu, struct perf_event_header *event) +{ + struct perf_event_sample *e = container_of(event, + struct perf_event_sample, + header); + struct perf_event_lost *lost = container_of(event, + struct perf_event_lost, + header); + struct event_pipe_ctx *ctx = private_data; + int idx = ctx->all_cpus ? cpu : ctx->idx; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "type"); + jsonw_uint(json_wtr, e->header.type); + jsonw_name(json_wtr, "cpu"); + jsonw_uint(json_wtr, cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, idx); + if (e->header.type == PERF_RECORD_SAMPLE) { + jsonw_name(json_wtr, "timestamp"); + jsonw_uint(json_wtr, e->time); + jsonw_name(json_wtr, "data"); + print_data_json(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + jsonw_name(json_wtr, "lost"); + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "id"); + jsonw_uint(json_wtr, lost->id); + jsonw_name(json_wtr, "count"); + jsonw_uint(json_wtr, lost->lost); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } else { + if (e->header.type == PERF_RECORD_SAMPLE) { + printf("== @%llu.%09llu CPU: %d index: %d =====\n", + e->time / 1000000000ULL, e->time % 1000000000ULL, + cpu, idx); + fprint_hex(stdout, e->data, e->size, " "); + printf("\n"); + } else if (e->header.type == PERF_RECORD_LOST) { + printf("lost %llu events\n", lost->lost); + } else { + printf("unknown event type=%u size=%u\n", + e->header.type, e->header.size); + } + } + + return LIBBPF_PERF_EVENT_CONT; +} + +int do_event_pipe(int argc, char **argv) +{ + struct perf_event_attr perf_attr = { + .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + .sample_period = 1, + .wakeup_events = 1, + }; + struct bpf_map_info map_info = {}; + LIBBPF_OPTS(perf_buffer_raw_opts, opts); + struct event_pipe_ctx ctx = { + .all_cpus = true, + .cpu = -1, + .idx = -1, + }; + struct perf_buffer *pb; + __u32 map_info_len; + int err, map_fd; + + map_info_len = sizeof(map_info); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len, + 0); + if (map_fd < 0) + return -1; + + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + p_err("map is not a perf event array"); + goto err_close_map; + } + + while (argc) { + if (argc < 2) { + BAD_ARG(); + goto err_close_map; + } + + if (is_prefix(*argv, "cpu")) { + char *endptr; + + NEXT_ARG(); + ctx.cpu = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as CPU ID", *argv); + goto err_close_map; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "index")) { + char *endptr; + + NEXT_ARG(); + ctx.idx = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as index", *argv); + goto err_close_map; + } + + NEXT_ARG(); + } else { + BAD_ARG(); + goto err_close_map; + } + + ctx.all_cpus = false; + } + + if (!ctx.all_cpus) { + if (ctx.idx == -1 || ctx.cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + } else { + ctx.cpu = 0; + ctx.idx = 0; + } + + opts.cpu_cnt = ctx.all_cpus ? 0 : 1; + opts.cpus = &ctx.cpu; + opts.map_keys = &ctx.idx; + pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, + print_bpf_output, &ctx, &opts); + if (!pb) { + p_err("failed to create perf buffer: %s (%d)", + strerror(errno), errno); + goto err_close_map; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + err = perf_buffer__poll(pb, 200); + if (err < 0 && err != -EINTR) { + p_err("perf buffer polling failed: %s (%d)", + strerror(errno), errno); + goto err_close_pb; + } + } + + if (json_output) + jsonw_end_array(json_wtr); + + perf_buffer__free(pb); + close(map_fd); + + return 0; + +err_close_pb: + perf_buffer__free(pb); +err_close_map: + close(map_fd); + return -1; +} diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c new file mode 100644 index 000000000..dba28755d --- /dev/null +++ b/tools/bpf/bpftool/net.c @@ -0,0 +1,1047 @@ +// 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/rtnetlink.h> +#include <linux/socket.h> +#include <linux/tc_act/tc_bpf.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> + +#include "bpf/nlattr.h" +#include "main.h" +#include "netlink_dumper.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +struct ip_devname_ifindex { + char devname[64]; + int ifindex; +}; + +struct bpf_netdev_t { + struct ip_devname_ifindex *devices; + int used_len; + int array_len; + int filter_idx; +}; + +struct tc_kind_handle { + char kind[64]; + int handle; +}; + +struct bpf_tcinfo_t { + struct tc_kind_handle *handle_array; + int used_len; + int array_len; + bool is_qdisc; +}; + +struct bpf_filter_t { + const char *kind; + const char *devname; + int ifindex; +}; + +struct bpf_attach_info { + __u32 flow_dissector_id; +}; + +enum net_attach_type { + NET_ATTACH_TYPE_XDP, + NET_ATTACH_TYPE_XDP_GENERIC, + NET_ATTACH_TYPE_XDP_DRIVER, + NET_ATTACH_TYPE_XDP_OFFLOAD, + NET_ATTACH_TYPE_TCX_INGRESS, + NET_ATTACH_TYPE_TCX_EGRESS, +}; + +static const char * const attach_type_strings[] = { + [NET_ATTACH_TYPE_XDP] = "xdp", + [NET_ATTACH_TYPE_XDP_GENERIC] = "xdpgeneric", + [NET_ATTACH_TYPE_XDP_DRIVER] = "xdpdrv", + [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", + [NET_ATTACH_TYPE_TCX_INGRESS] = "tcx_ingress", + [NET_ATTACH_TYPE_TCX_EGRESS] = "tcx_egress", +}; + +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) +{ + enum net_attach_type type; + + for (type = 0; type < net_attach_type_size; type++) { + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return net_attach_type_size; +} + +typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t, void *cookie); + +static int netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + p_err("Netlink error reporting not supported"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, + __dump_nlmsg_t _fn, dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[8192]; + 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; + } + } + + if (len) + p_err("Invalid message or trailing data in Netlink response: %d bytes left", len); + } + ret = 0; +done: + return ret; +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +static int netlink_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +static int netlink_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +static int netlink_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +static int netlink_get_link(int sock, unsigned int nl_pid, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + +static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_netdev_t *netinfo = cookie; + struct ifinfomsg *ifinfo = msg; + struct ip_devname_ifindex *tmp; + + if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index) + return 0; + + if (netinfo->used_len == netinfo->array_len) { + tmp = realloc(netinfo->devices, + (netinfo->array_len + 16) * sizeof(struct ip_devname_ifindex)); + if (!tmp) + return -ENOMEM; + + netinfo->devices = tmp; + netinfo->array_len += 16; + } + netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index; + snprintf(netinfo->devices[netinfo->used_len].devname, + sizeof(netinfo->devices[netinfo->used_len].devname), + "%s", + tb[IFLA_IFNAME] + ? libbpf_nla_getattr_str(tb[IFLA_IFNAME]) + : ""); + netinfo->used_len++; + + return do_xdp_dump(ifinfo, tb); +} + +static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_tcinfo_t *tcinfo = cookie; + struct tcmsg *info = msg; + struct tc_kind_handle *tmp; + + if (tcinfo->is_qdisc) { + /* skip clsact qdisc */ + if (tb[TCA_KIND] && + strcmp(libbpf_nla_data(tb[TCA_KIND]), "clsact") == 0) + return 0; + if (info->tcm_handle == 0) + return 0; + } + + if (tcinfo->used_len == tcinfo->array_len) { + tmp = realloc(tcinfo->handle_array, + (tcinfo->array_len + 16) * sizeof(struct tc_kind_handle)); + if (!tmp) + return -ENOMEM; + + tcinfo->handle_array = tmp; + tcinfo->array_len += 16; + } + tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle; + snprintf(tcinfo->handle_array[tcinfo->used_len].kind, + sizeof(tcinfo->handle_array[tcinfo->used_len].kind), + "%s", + tb[TCA_KIND] + ? libbpf_nla_getattr_str(tb[TCA_KIND]) + : "unknown"); + tcinfo->used_len++; + + return 0; +} + +static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + const struct bpf_filter_t *filter_info = cookie; + + return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind, + filter_info->devname, filter_info->ifindex); +} + +static int __show_dev_tc_bpf_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)", (unsigned int)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] & (1U << j))) + continue; + NET_DUMP_UINT_ONLY(1U << 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] & (1U << j))) + continue; + NET_DUMP_UINT_ONLY(1U << 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; + int i, handle, ret = 0; + + tcinfo.handle_array = NULL; + tcinfo.used_len = 0; + tcinfo.array_len = 0; + + tcinfo.is_qdisc = false; + ret = netlink_get_class(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); + if (ret) + goto out; + + tcinfo.is_qdisc = true; + ret = netlink_get_qdisc(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); + if (ret) + goto out; + + filter_info.devname = dev->devname; + filter_info.ifindex = dev->ifindex; + for (i = 0; i < tcinfo.used_len; i++) { + filter_info.kind = tcinfo.handle_array[i].kind; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, + tcinfo.handle_array[i].handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + } + + /* root, ingress and egress handle */ + handle = TC_H_ROOT; + filter_info.kind = "root"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + filter_info.kind = "clsact/ingress"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS); + filter_info.kind = "clsact/egress"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + +out: + free(tcinfo.handle_array); + return 0; +} + +static int query_flow_dissector(struct bpf_attach_info *attach_info) +{ + __u32 attach_flags; + __u32 prog_ids[1]; + __u32 prog_cnt; + int err; + int fd; + + fd = open("/proc/self/ns/net", O_RDONLY); + if (fd < 0) { + p_err("can't open /proc/self/ns/net: %s", + strerror(errno)); + return -1; + } + prog_cnt = ARRAY_SIZE(prog_ids); + err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0, + &attach_flags, prog_ids, &prog_cnt); + close(fd); + if (err) { + if (err == -EINVAL) { + /* Older kernel's don't support querying + * flow dissector programs. + */ + errno = 0; + return 0; + } + p_err("can't query prog: %s", strerror(-err)); + return -1; + } + + if (prog_cnt == 1) + attach_info->flow_dissector_id = prog_ids[0]; + + return 0; +} + +static int net_parse_dev(int *argc, char ***argv) +{ + int ifindex; + + if (is_prefix(**argv, "dev")) { + NEXT_ARGP(); + + ifindex = if_nametoindex(**argv); + if (!ifindex) + p_err("invalid devname %s", **argv); + + NEXT_ARGP(); + } else { + p_err("expected 'dev', got: '%s'?", **argv); + return -1; + } + + return ifindex; +} + +static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, + int ifindex, bool overwrite) +{ + __u32 flags = 0; + + if (!overwrite) + flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (attach_type == NET_ATTACH_TYPE_XDP_GENERIC) + flags |= XDP_FLAGS_SKB_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_DRIVER) + flags |= XDP_FLAGS_DRV_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) + flags |= XDP_FLAGS_HW_MODE; + + return bpf_xdp_attach(ifindex, progfd, flags, NULL); +} + +static int get_tcx_type(enum net_attach_type attach_type) +{ + switch (attach_type) { + case NET_ATTACH_TYPE_TCX_INGRESS: + return BPF_TCX_INGRESS; + case NET_ATTACH_TYPE_TCX_EGRESS: + return BPF_TCX_EGRESS; + default: + return -1; + } +} + +static int do_attach_tcx(int progfd, enum net_attach_type attach_type, int ifindex, bool prepend) +{ + int type = get_tcx_type(attach_type); + + if (prepend) { + LIBBPF_OPTS(bpf_prog_attach_opts, opts, + .flags = BPF_F_BEFORE + ); + return bpf_prog_attach_opts(progfd, ifindex, type, &opts); + } + return bpf_prog_attach(progfd, ifindex, type, 0); +} + +static int do_detach_tcx(int targetfd, enum net_attach_type attach_type) +{ + int type = get_tcx_type(attach_type); + + return bpf_prog_detach(targetfd, type); +} + +static int do_attach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + bool overwrite = false; + bool prepend = false; + + /* parse attach args */ + if (!REQ_ARGS(5)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + progfd = prog_parse_fd(&argc, &argv); + if (progfd < 0) + return -EINVAL; + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) { + err = -EINVAL; + goto cleanup; + } + + if (argc) { + if (is_prefix(*argv, "overwrite")) { + if (attach_type != NET_ATTACH_TYPE_XDP && + attach_type != NET_ATTACH_TYPE_XDP_GENERIC && + attach_type != NET_ATTACH_TYPE_XDP_DRIVER && + attach_type != NET_ATTACH_TYPE_XDP_OFFLOAD) { + p_err("'overwrite' is only supported for xdp types"); + err = -EINVAL; + goto cleanup; + } + overwrite = true; + } else if (is_prefix(*argv, "prepend")) { + if (attach_type != NET_ATTACH_TYPE_TCX_INGRESS && + attach_type != NET_ATTACH_TYPE_TCX_EGRESS) { + p_err("'prepend' is only supported for tcx_ingress/tcx_egress"); + err = -EINVAL; + goto cleanup; + } + prepend = true; + } else { + p_err("expected 'overwrite' or 'prepend', got: '%s'?", *argv); + err = -EINVAL; + goto cleanup; + } + } + + switch (attach_type) { + /* attach xdp prog */ + case NET_ATTACH_TYPE_XDP: + case NET_ATTACH_TYPE_XDP_GENERIC: + case NET_ATTACH_TYPE_XDP_DRIVER: + case NET_ATTACH_TYPE_XDP_OFFLOAD: + err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); + break; + /* attach tcx prog */ + case NET_ATTACH_TYPE_TCX_INGRESS: + case NET_ATTACH_TYPE_TCX_EGRESS: + err = do_attach_tcx(progfd, attach_type, ifindex, prepend); + break; + default: + break; + } + + if (err) { + p_err("interface %s attach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + goto cleanup; + } + + if (json_output) + jsonw_null(json_wtr); +cleanup: + close(progfd); + return err; +} + +static int do_detach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + + /* parse detach args */ + if (!REQ_ARGS(3)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) + return -EINVAL; + + switch (attach_type) { + /* detach xdp prog */ + case NET_ATTACH_TYPE_XDP: + case NET_ATTACH_TYPE_XDP_GENERIC: + case NET_ATTACH_TYPE_XDP_DRIVER: + case NET_ATTACH_TYPE_XDP_OFFLOAD: + progfd = -1; + err = do_attach_detach_xdp(progfd, attach_type, ifindex, NULL); + break; + /* detach tcx prog */ + case NET_ATTACH_TYPE_TCX_INGRESS: + case NET_ATTACH_TYPE_TCX_EGRESS: + err = do_detach_tcx(ifindex, attach_type); + break; + default: + break; + } + + if (err < 0) { + p_err("interface %s detach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int 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 %u)", 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++; + } + + if (!nf_link_info) + return; + + 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 = 0; + char err_buf[256]; + + if (argc == 2) { + filter_idx = net_parse_dev(&argc, &argv); + if (filter_idx < 1) + return -1; + } else if (argc != 0) { + usage(); + } + + ret = query_flow_dissector(&attach_info); + if (ret) + return -1; + + sock = netlink_open(&nl_pid); + if (sock < 0) { + fprintf(stderr, "failed to open netlink sock\n"); + return -1; + } + + dev_array.devices = NULL; + dev_array.used_len = 0; + dev_array.array_len = 0; + dev_array.filter_idx = filter_idx; + + if (json_output) + jsonw_start_array(json_wtr); + NET_START_OBJECT; + NET_START_ARRAY("xdp", "%s:\n"); + ret = netlink_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); + NET_END_ARRAY("\n"); + + if (!ret) { + NET_START_ARRAY("tc", "%s:\n"); + for (i = 0; i < dev_array.used_len; i++) { + show_dev_tc_bpf(&dev_array.devices[i]); + ret = show_dev_tc_bpf_classic(sock, nl_pid, + &dev_array.devices[i]); + if (ret) + break; + } + NET_END_ARRAY("\n"); + } + + NET_START_ARRAY("flow_dissector", "%s:\n"); + if (attach_info.flow_dissector_id > 0) + NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); + NET_END_ARRAY("\n"); + + NET_START_ARRAY("netfilter", "%s:\n"); + show_link_netfilter(); + NET_END_ARRAY("\n"); + + NET_END_OBJECT; + if (json_output) + jsonw_end_array(json_wtr); + + if (ret) { + if (json_output) + jsonw_null(json_wtr); + libbpf_strerror(ret, err_buf, sizeof(err_buf)); + fprintf(stderr, "Error: %s\n", err_buf); + } + free(dev_array.devices); + close(sock); + return ret; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [dev <devname>]\n" + " %1$s %2$s attach ATTACH_TYPE PROG dev <devname> [ overwrite | prepend ]\n" + " %1$s %2$s detach ATTACH_TYPE dev <devname>\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_PROGRAM "\n" + " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload | tcx_ingress\n" + " | tcx_egress }\n" + " " HELP_SPEC_OPTIONS " }\n" + "\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" + " consult iproute2.\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "attach", do_attach }, + { "detach", do_detach }, + { "help", do_help }, + { 0 } +}; + +int do_net(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c new file mode 100644 index 000000000..0a3c7e96c --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2018 Facebook + +#include <stdlib.h> +#include <string.h> +#include <bpf/libbpf.h> +#include <linux/rtnetlink.h> +#include <linux/tc_act/tc_bpf.h> + +#include "bpf/nlattr.h" +#include "main.h" +#include "netlink_dumper.h" + +static void xdp_dump_prog_id(struct nlattr **tb, int attr, + const char *mode, + bool new_json_object) +{ + if (!tb[attr]) + return; + + if (new_json_object) + NET_START_OBJECT + NET_DUMP_STR("mode", " %s", mode); + NET_DUMP_UINT("id", " id %u", libbpf_nla_getattr_u32(tb[attr])) + if (new_json_object) + NET_END_OBJECT +} + +static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex, + const char *name) +{ + struct nlattr *tb[IFLA_XDP_MAX + 1]; + unsigned char mode; + + if (libbpf_nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0) + return -1; + + if (!tb[IFLA_XDP_ATTACHED]) + return 0; + + mode = libbpf_nla_getattr_u8(tb[IFLA_XDP_ATTACHED]); + if (mode == XDP_ATTACHED_NONE) + return 0; + + NET_START_OBJECT; + if (name) + NET_DUMP_STR("devname", "%s", name); + NET_DUMP_UINT("ifindex", "(%u)", ifindex); + + if (mode == XDP_ATTACHED_MULTI) { + if (json_output) { + jsonw_name(json_wtr, "multi_attachments"); + jsonw_start_array(json_wtr); + } + xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true); + xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true); + xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true); + if (json_output) + jsonw_end_array(json_wtr); + } else if (mode == XDP_ATTACHED_DRV) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false); + } else if (mode == XDP_ATTACHED_SKB) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false); + } else if (mode == XDP_ATTACHED_HW) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false); + } + + NET_END_OBJECT_FINAL; + return 0; +} + +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb) +{ + if (!tb[IFLA_XDP]) + return 0; + + return do_xdp_dump_one(tb[IFLA_XDP], (unsigned int)ifinfo->ifi_index, + libbpf_nla_getattr_str(tb[IFLA_IFNAME])); +} + +static int do_bpf_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (!tb[TCA_ACT_BPF_PARMS]) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_OBJECT_NESTED2; + if (tb[TCA_ACT_BPF_NAME]) + NET_DUMP_STR("name", "%s", + libbpf_nla_getattr_str(tb[TCA_ACT_BPF_NAME])); + if (tb[TCA_ACT_BPF_ID]) + NET_DUMP_UINT("id", " id %u", + libbpf_nla_getattr_u32(tb[TCA_ACT_BPF_ID])); + NET_END_OBJECT_NESTED; + return 0; +} + +static int do_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX + 1]; + + if (!attr) + return 0; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_ACT_KIND] && + strcmp(libbpf_nla_data(tb[TCA_ACT_KIND]), "bpf") == 0) + return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]); + + return 0; +} + +static int do_bpf_act_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; + int act, ret; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_ARRAY("act", " %s ["); + for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) { + ret = do_dump_one_act(tb[act]); + if (ret) + break; + } + NET_END_ARRAY("] "); + + return ret; +} + +static int do_bpf_filter_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_BPF_MAX + 1]; + int ret; + + if (libbpf_nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_BPF_NAME]) + NET_DUMP_STR("name", " %s", + libbpf_nla_getattr_str(tb[TCA_BPF_NAME])); + if (tb[TCA_BPF_ID]) + NET_DUMP_UINT("id", " id %u", + libbpf_nla_getattr_u32(tb[TCA_BPF_ID])); + if (tb[TCA_BPF_ACT]) { + ret = do_bpf_act_dump(tb[TCA_BPF_ACT]); + if (ret) + return ret; + } + + return 0; +} + +int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind, + const char *devname, int ifindex) +{ + int ret = 0; + + if (tb[TCA_OPTIONS] && + strcmp(libbpf_nla_data(tb[TCA_KIND]), "bpf") == 0) { + NET_START_OBJECT; + if (devname[0] != '\0') + NET_DUMP_STR("devname", "%s", devname); + NET_DUMP_UINT("ifindex", "(%u)", (unsigned int)ifindex); + NET_DUMP_STR("kind", " %s", kind); + ret = do_bpf_filter_dump(tb[TCA_OPTIONS]); + NET_END_OBJECT_FINAL; + } + + return ret; +} diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h new file mode 100644 index 000000000..96318106f --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +// Copyright (C) 2018 Facebook + +#ifndef _NETLINK_DUMPER_H_ +#define _NETLINK_DUMPER_H_ + +#define NET_START_OBJECT \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ +} + +#define NET_START_OBJECT_NESTED(name) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_object(json_wtr); \ + } else { \ + fprintf(stdout, "%s {", name); \ + } \ +} + +#define NET_START_OBJECT_NESTED2 \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ + else \ + fprintf(stdout, "{"); \ +} + +#define NET_END_OBJECT_NESTED \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "}"); \ +} + +#define NET_END_OBJECT \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ +} + +#define NET_END_OBJECT_FINAL \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "\n"); \ +} + +#define NET_START_ARRAY(name, fmt_str) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_array(json_wtr); \ + } else { \ + fprintf(stdout, fmt_str, name); \ + } \ +} + +#define NET_END_ARRAY(endstr) \ +{ \ + if (json_output) \ + jsonw_end_array(json_wtr); \ + else \ + fprintf(stdout, "%s", endstr); \ +} + +#define NET_DUMP_UINT(name, fmt_str, val) \ +{ \ + if (json_output) \ + jsonw_uint_field(json_wtr, name, val); \ + else \ + fprintf(stdout, fmt_str, val); \ +} + +#define NET_DUMP_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) \ + jsonw_string_field(json_wtr, name, str);\ + else \ + fprintf(stdout, fmt_str, str); \ +} + +#define NET_DUMP_STR_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_string(json_wtr, str); \ + else \ + fprintf(stdout, "%s ", str); \ +} + +#endif diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c new file mode 100644 index 000000000..80de2874d --- /dev/null +++ b/tools/bpf/bpftool/perf.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// 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> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <dirent.h> + +#include <bpf/bpf.h> + +#include "main.h" + +/* 0: undecided, 1: supported, 2: not supported */ +static int perf_query_supported; +static bool has_perf_query_support(void) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + char buf[256]; + int fd; + + if (perf_query_supported) + goto out; + + fd = open("/", O_RDONLY); + if (fd < 0) { + p_err("perf_query_support: cannot open directory \"/\" (%s)", + strerror(errno)); + goto out; + } + + /* the following query will fail as no bpf attachment, + * the expected errno is ENOTSUPP + */ + errno = 0; + len = sizeof(buf); + bpf_task_fd_query(getpid(), fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + + if (errno == 524 /* ENOTSUPP */) { + perf_query_supported = 1; + goto close_fd; + } + + perf_query_supported = 2; + p_err("perf_query_support: %s", strerror(errno)); + fprintf(stderr, + "HINT: non root or kernel doesn't support TASK_FD_QUERY\n"); + +close_fd: + close(fd); +out: + return perf_query_supported == 1; +} + +static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + jsonw_start_object(json_wtr); + jsonw_int_field(json_wtr, "pid", pid); + jsonw_int_field(json_wtr, "fd", fd); + jsonw_uint_field(json_wtr, "prog_id", prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "raw_tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_KPROBE: + jsonw_string_field(json_wtr, "fd_type", "kprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_KRETPROBE: + jsonw_string_field(json_wtr, "fd_type", "kretprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_UPROBE: + jsonw_string_field(json_wtr, "fd_type", "uprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + jsonw_string_field(json_wtr, "fd_type", "uretprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + default: + break; + } + jsonw_end_object(json_wtr); +} + +static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + printf("pid %d fd %d: prog_id %u ", pid, fd, prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + printf("raw_tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + printf("tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_KPROBE: + if (buf[0] != '\0') + printf("kprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_KRETPROBE: + if (buf[0] != '\0') + printf("kretprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kretprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_UPROBE: + printf("uprobe filename %s offset %llu\n", buf, probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + printf("uretprobe filename %s offset %llu\n", buf, + probe_offset); + break; + default: + break; + } +} + +static int show_proc(void) +{ + struct dirent *proc_de, *pid_fd_de; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + DIR *proc, *pid_fd; + int err, pid, fd; + const char *pch; + char buf[4096]; + + proc = opendir("/proc"); + if (!proc) + return -1; + + while ((proc_de = readdir(proc))) { + pid = 0; + pch = proc_de->d_name; + + /* pid should be all numbers */ + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + err = snprintf(buf, sizeof(buf), "/proc/%s/fd", proc_de->d_name); + if (err < 0 || err >= (int)sizeof(buf)) + continue; + + pid_fd = opendir(buf); + if (!pid_fd) + continue; + + while ((pid_fd_de = readdir(pid_fd))) { + fd = 0; + pch = pid_fd_de->d_name; + + /* fd should be all numbers */ + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, + &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + continue; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + } + closedir(pid_fd); + } + closedir(proc); + return 0; +} + +static int do_show(int argc, char **argv) +{ + int err; + + if (!has_perf_query_support()) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + err = show_proc(); + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %1$s %2$s { show | list }\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_perf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c new file mode 100644 index 000000000..23f488cf1 --- /dev/null +++ b/tools/bpf/bpftool/pids.c @@ -0,0 +1,263 @@ +// 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)); + ref->comm[sizeof(ref->comm) - 1] = '\0'; + 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)); + ref->comm[sizeof(ref->comm) - 1] = '\0'; + 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; + + *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; + + if (!verifier_logs) { + libbpf_print_fn_t default_print; + + /* Unless debug information is on, we don't want the output to + * be 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); + } else { + err = pid_iter_bpf__load(skel); + } + 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 new file mode 100644 index 000000000..a9f730d40 --- /dev/null +++ b/tools/bpf/bpftool/prog.c @@ -0,0 +1,2618 @@ +// 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> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/ioctl.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <dirent.h> + +#include <linux/err.h> +#include <linux/perf_event.h> +#include <linux/sizes.h> +#include <linux/keyctl.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> +#include <bpf/skel_internal.h> + +#include "cfg.h" +#include "main.h" +#include "xlated_dumper.h" + +#define BPF_METADATA_PREFIX "bpf_metadata_" +#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) + +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + +static const bool attach_types[] = { + [BPF_SK_SKB_STREAM_PARSER] = true, + [BPF_SK_SKB_STREAM_VERDICT] = true, + [BPF_SK_SKB_VERDICT] = true, + [BPF_SK_MSG_VERDICT] = true, + [BPF_FLOW_DISSECTOR] = true, + [__MAX_BPF_ATTACH_TYPE] = false, +}; + +/* Textual representations traditionally used by the program and kept around + * for the sake of backwards compatibility. + */ +static const char * const attach_type_strings[] = { + [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", + [BPF_SK_SKB_VERDICT] = "skb_verdict", + [BPF_SK_MSG_VERDICT] = "msg_verdict", + [__MAX_BPF_ATTACH_TYPE] = NULL, +}; + +static struct hashmap *prog_table; + +static enum bpf_attach_type parse_attach_type(const char *str) +{ + enum bpf_attach_type type; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_types[type]) { + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!strcmp(str, attach_type_str)) + return type; + } + + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return __MAX_BPF_ATTACH_TYPE; +} + +static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode, + void **info_data, size_t *const info_data_sz) +{ + struct bpf_prog_info holder = {}; + size_t needed = 0; + void *ptr; + + if (mode == DUMP_JITED) { + holder.jited_prog_len = info->jited_prog_len; + needed += info->jited_prog_len; + } else { + holder.xlated_prog_len = info->xlated_prog_len; + needed += info->xlated_prog_len; + } + + holder.nr_jited_ksyms = info->nr_jited_ksyms; + needed += info->nr_jited_ksyms * sizeof(__u64); + + holder.nr_jited_func_lens = info->nr_jited_func_lens; + needed += info->nr_jited_func_lens * sizeof(__u32); + + holder.nr_func_info = info->nr_func_info; + holder.func_info_rec_size = info->func_info_rec_size; + needed += info->nr_func_info * info->func_info_rec_size; + + holder.nr_line_info = info->nr_line_info; + holder.line_info_rec_size = info->line_info_rec_size; + needed += info->nr_line_info * info->line_info_rec_size; + + holder.nr_jited_line_info = info->nr_jited_line_info; + holder.jited_line_info_rec_size = info->jited_line_info_rec_size; + needed += info->nr_jited_line_info * info->jited_line_info_rec_size; + + if (needed > *info_data_sz) { + ptr = realloc(*info_data, needed); + if (!ptr) + return -1; + + *info_data = ptr; + *info_data_sz = needed; + } + ptr = *info_data; + + if (mode == DUMP_JITED) { + holder.jited_prog_insns = ptr_to_u64(ptr); + ptr += holder.jited_prog_len; + } else { + holder.xlated_prog_insns = ptr_to_u64(ptr); + ptr += holder.xlated_prog_len; + } + + holder.jited_ksyms = ptr_to_u64(ptr); + ptr += holder.nr_jited_ksyms * sizeof(__u64); + + holder.jited_func_lens = ptr_to_u64(ptr); + ptr += holder.nr_jited_func_lens * sizeof(__u32); + + holder.func_info = ptr_to_u64(ptr); + ptr += holder.nr_func_info * holder.func_info_rec_size; + + holder.line_info = ptr_to_u64(ptr); + ptr += holder.nr_line_info * holder.line_info_rec_size; + + holder.jited_line_info = ptr_to_u64(ptr); + ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size; + + *info = holder; + return 0; +} + +static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) +{ + struct timespec real_time_ts, boot_time_ts; + time_t wallclock_secs; + struct tm load_tm; + + buf[--size] = '\0'; + + if (clock_gettime(CLOCK_REALTIME, &real_time_ts) || + clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) { + perror("Can't read clocks"); + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + + (real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) / + 1000000000; + + + if (!localtime_r(&wallclock_secs, &load_tm)) { + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); +} + +static void show_prog_maps(int fd, __u32 num_maps) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + __u32 map_ids[num_maps]; + unsigned int i; + int err; + + info.nr_map_ids = num_maps; + info.map_ids = ptr_to_u64(map_ids); + + err = bpf_prog_get_info_by_fd(fd, &info, &len); + if (err || !info.nr_map_ids) + return; + + if (json_output) { + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); + for (i = 0; i < info.nr_map_ids; i++) + jsonw_uint(json_wtr, map_ids[i]); + jsonw_end_array(json_wtr); + } else { + printf(" map_ids "); + for (i = 0; i < info.nr_map_ids; i++) + printf("%u%s", map_ids[i], + i == info.nr_map_ids - 1 ? "" : ","); + } +} + +static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) +{ + struct bpf_prog_info prog_info; + __u32 prog_info_len; + __u32 map_info_len; + void *value = NULL; + __u32 *map_ids; + int nr_maps; + int key = 0; + int map_fd; + int ret; + __u32 i; + + memset(&prog_info, 0, sizeof(prog_info)); + prog_info_len = sizeof(prog_info); + ret = bpf_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 (map_info->type != BPF_MAP_TYPE_ARRAY || + map_info->key_size != sizeof(int) || + map_info->max_entries != 1 || + !map_info->btf_value_type_id || + !strstr(map_info->name, ".rodata")) { + close(map_fd); + continue; + } + + value = malloc(map_info->value_size); + if (!value) { + close(map_fd); + goto free_map_ids; + } + + if (bpf_map_lookup_elem(map_fd, &key, value)) { + close(map_fd); + free(value); + value = NULL; + goto free_map_ids; + } + + close(map_fd); + break; + } + +free_map_ids: + free(map_ids); + return value; +} + +static bool has_metadata_prefix(const char *s) +{ + return strncmp(s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) == 0; +} + +static void show_prog_metadata(int fd, __u32 num_maps) +{ + const struct btf_type *t_datasec, *t_var; + struct bpf_map_info map_info; + struct btf_var_secinfo *vsi; + bool printed_header = false; + unsigned int i, vlen; + void *value = NULL; + const char *name; + struct btf *btf; + int err; + + if (!num_maps) + return; + + memset(&map_info, 0, sizeof(map_info)); + value = find_metadata(fd, &map_info); + if (!value) + return; + + btf = btf__load_from_kernel_by_id(map_info.btf_id); + if (!btf) + goto out_free; + + t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id); + if (!btf_is_datasec(t_datasec)) + goto out_free; + + vlen = btf_vlen(t_datasec); + vsi = btf_var_secinfos(t_datasec); + + /* We don't proceed to check the kinds of the elements of the DATASEC. + * The verifier enforces them to be BTF_KIND_VAR. + */ + + if (json_output) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); + + if (!has_metadata_prefix(name)) + continue; + + if (!printed_header) { + jsonw_name(json_wtr, "metadata"); + jsonw_start_object(json_wtr); + printed_header = true; + } + + jsonw_name(json_wtr, name + BPF_METADATA_PREFIX_LEN); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_end_object(json_wtr); + } else { + json_writer_t *btf_wtr; + struct btf_dumper d = { + .btf = btf, + .is_plain_text = true, + }; + + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); + + if (!has_metadata_prefix(name)) + continue; + + if (!printed_header) { + printf("\tmetadata:"); + + btf_wtr = jsonw_new(stdout); + if (!btf_wtr) { + p_err("jsonw alloc failed"); + goto out_free; + } + d.jw = btf_wtr, + + printed_header = true; + } + + printf("\n\t\t%s = ", name + BPF_METADATA_PREFIX_LEN); + + jsonw_reset(btf_wtr); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_destroy(&btf_wtr); + } + +out_free: + btf__free(btf); + free(value); +} + +static void print_prog_header_json(struct bpf_prog_info *info, int fd) +{ + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + + jsonw_uint_field(json_wtr, "id", info->id); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + + if (prog_type_str) + jsonw_string_field(json_wtr, "type", prog_type_str); + else + jsonw_uint_field(json_wtr, "type", info->type); + + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } + + jsonw_name(json_wtr, "tag"); + jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", + info->tag[0], info->tag[1], info->tag[2], info->tag[3], + info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + if (info->run_time_ns) { + jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); + jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); + } + if (info->recursion_misses) + jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses); +} + +static void print_prog_json(struct bpf_prog_info *info, int fd, bool orphaned) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info, fd); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); + + if (info->load_time) { + char buf[32]; + + print_boot_time(info->load_time, buf, sizeof(buf)); + + /* Piggy back on load_time, since 0 uid is a valid one */ + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); + jsonw_uint_field(json_wtr, "uid", info->created_by_uid); + } + + jsonw_bool_field(json_wtr, "orphaned", orphaned); + jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len); + + if (info->jited_prog_len) { + jsonw_bool_field(json_wtr, "jited", true); + jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len); + } else { + jsonw_bool_field(json_wtr, "jited", false); + } + + memlock = get_fdinfo(fd, "memlock"); + if (memlock) + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); + free(memlock); + + if (info->nr_map_ids) + show_prog_maps(fd, info->nr_map_ids); + + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(prog_table, entry, 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, int fd) +{ + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + + printf("%u: ", info->id); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + if (prog_type_str) + printf("%s ", prog_type_str); + else + printf("type %u ", info->type); + + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } + + printf("tag "); + fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); + print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); + if (info->run_time_ns) + printf(" run_time_ns %llu run_cnt %llu", + info->run_time_ns, info->run_cnt); + if (info->recursion_misses) + printf(" recursion_misses %llu", info->recursion_misses); + printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd, bool orphaned) +{ + char *memlock; + + print_prog_header_plain(info, fd); + + if (info->load_time) { + char buf[32]; + + print_boot_time(info->load_time, buf, sizeof(buf)); + + /* Piggy back on load_time, since 0 uid is a valid one */ + printf("\tloaded_at %s uid %u\n", buf, info->created_by_uid); + } + + printf("\txlated %uB", info->xlated_prog_len); + + if (info->jited_prog_len) + printf(" jited %uB", info->jited_prog_len); + else + printf(" not jited"); + + memlock = get_fdinfo(fd, "memlock"); + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + if (orphaned) + printf(" orphaned"); + + if (info->nr_map_ids) + show_prog_maps(fd, info->nr_map_ids); + + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; + + hashmap__for_each_key_entry(prog_table, entry, info->id) + printf("\n\tpinned %s", (char *)entry->pvalue); + } + + if (info->btf_id) + printf("\n\tbtf_id %u", info->btf_id); + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); + + show_prog_metadata(fd, info->nr_map_ids); +} + +static int show_prog(int fd) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + int err; + + err = bpf_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, err == -ENODEV); + else + print_prog_plain(&info, fd, err == -ENODEV); + + return 0; +} + +static int do_show_subset(int argc, char **argv) +{ + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = show_prog(fds[i]); + if (err) { + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err; + int fd; + + if (show_pinned) { + prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(prog_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(prog_table, BPF_OBJ_PROG); + } + build_obj_refs_table(&refs_table, BPF_OBJ_PROG); + + if (argc == 2) + return do_show_subset(argc, argv); + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next program: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + err = -1; + break; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + err = -1; + break; + } + + err = show_prog(fd); + close(fd); + if (err) + break; + } + + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(prog_table); + + return err; +} + +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) +{ + struct bpf_prog_linfo *prog_linfo = NULL; + const char *disasm_opt = NULL; + struct dump_data dd = {}; + void *func_info = NULL; + struct btf *btf = NULL; + char func_sig[1024]; + unsigned char *buf; + __u32 member_len; + int fd, err = -1; + ssize_t n; + + if (mode == DUMP_JITED) { + if (info->jited_prog_len == 0 || !info->jited_prog_insns) { + p_err("error retrieving jit dump: no instructions returned or kernel.kptr_restrict set?"); + return -1; + } + buf = u64_to_ptr(info->jited_prog_insns); + member_len = info->jited_prog_len; + } else { /* DUMP_XLATED */ + if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { + p_err("error retrieving insn dump: kernel.kptr_restrict set?"); + return -1; + } + buf = u64_to_ptr(info->xlated_prog_insns); + member_len = info->xlated_prog_len; + } + + if (info->btf_id) { + btf = btf__load_from_kernel_by_id(info->btf_id); + if (!btf) { + p_err("failed to get btf"); + return -1; + } + } + + func_info = u64_to_ptr(info->func_info); + + if (info->nr_line_info) { + prog_linfo = bpf_prog_linfo__new(info); + if (!prog_linfo) + p_info("error in processing bpf_line_info. continue without it."); + } + + if (filepath) { + fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600); + if (fd < 0) { + p_err("can't open file %s: %s", filepath, + strerror(errno)); + goto exit_free; + } + + n = write(fd, buf, member_len); + close(fd); + if (n != (ssize_t)member_len) { + p_err("error writing output file: %s", + n < 0 ? strerror(errno) : "short write"); + goto exit_free; + } + + if (json_output) + jsonw_null(json_wtr); + } else if (mode == DUMP_JITED) { + const char *name = NULL; + + if (info->ifindex) { + name = ifindex_to_arch(info->ifindex, info->netns_dev, + info->netns_ino, &disasm_opt); + if (!name) + goto exit_free; + } + + if (info->nr_jited_func_lens && info->jited_func_lens) { + struct kernel_sym *sym = NULL; + struct bpf_func_info *record; + char sym_name[SYM_MAX_NAME]; + unsigned char *img = buf; + __u64 *ksyms = NULL; + __u32 *lens; + __u32 i; + if (info->nr_jited_ksyms) { + kernel_syms_load(&dd); + ksyms = u64_to_ptr(info->jited_ksyms); + } + + if (json_output) + jsonw_start_array(json_wtr); + + lens = u64_to_ptr(info->jited_func_lens); + for (i = 0; i < info->nr_jited_func_lens; i++) { + if (ksyms) { + sym = kernel_syms_search(&dd, ksyms[i]); + if (sym) + sprintf(sym_name, "%s", sym->name); + else + sprintf(sym_name, "0x%016llx", ksyms[i]); + } else { + strcpy(sym_name, "unknown"); + } + + if (func_info) { + record = func_info + i * info->func_info_rec_size; + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + } + + if (json_output) { + jsonw_start_object(json_wtr); + if (func_info && func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } + jsonw_name(json_wtr, "name"); + jsonw_string(json_wtr, sym_name); + jsonw_name(json_wtr, "insns"); + } else { + if (func_info && func_sig[0] != '\0') + printf("%s:\n", func_sig); + printf("%s:\n", sym_name); + } + + if (ksyms) { + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + prog_linfo, ksyms[i], i, + linum)) + goto exit_free; + } else { + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + NULL, 0, 0, false)) + goto exit_free; + } + + img += lens[i]; + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + } + + if (json_output) + jsonw_end_array(json_wtr); + } else { + if (disasm_print_insn(buf, member_len, opcodes, name, + disasm_opt, btf, NULL, 0, 0, + false)) + goto exit_free; + } + } else { + kernel_syms_load(&dd); + dd.nr_jited_ksyms = info->nr_jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); + dd.btf = btf; + dd.func_info = func_info; + dd.finfo_rec_size = info->func_info_rec_size; + dd.prog_linfo = prog_linfo; + + if (json_output) + dump_xlated_json(&dd, buf, member_len, opcodes, linum); + else if (visual) + dump_xlated_cfg(&dd, buf, member_len, opcodes, linum); + else + dump_xlated_plain(&dd, buf, member_len, opcodes, linum); + kernel_syms_destroy(&dd); + } + + err = 0; + +exit_free: + btf__free(btf); + bpf_prog_linfo__free(prog_linfo); + return err; +} + +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + size_t info_data_sz = 0; + void *info_data = NULL; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int nb_fds, i = 0; + int *fds = NULL; + int err = -1; + + if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + mode = DUMP_JITED; + } else if (is_prefix(*argv, "xlated")) { + mode = DUMP_XLATED; + } else { + p_err("expected 'xlated' or 'jited', got: %s", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + 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"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } else { + usage(); + goto exit_close; + } + } + + 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 (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + memset(&info, 0, sizeof(info)); + + err = bpf_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, fds[i]); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info, fds[i]); + } + + err = prog_dump(&info, mode, filepath, opcodes, visual, linum); + + if (json_output && nb_fds > 1) + jsonw_end_object(json_wtr); /* prog object */ + else if (i != nb_fds - 1 && nb_fds > 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(info_data); + free(fds); + return err; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, prog_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +struct map_replace { + int idx; + int fd; + char *name; +}; + +static int map_replace_compar(const void *p1, const void *p2) +{ + const struct map_replace *a = p1, *b = p2; + + return a->idx - b->idx; +} + +static int parse_attach_detach_args(int argc, char **argv, int *progfd, + enum bpf_attach_type *attach_type, + int *mapfd) +{ + if (!REQ_ARGS(3)) + return -EINVAL; + + *progfd = prog_parse_fd(&argc, &argv); + if (*progfd < 0) + return *progfd; + + *attach_type = parse_attach_type(*argv); + if (*attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach/detach type"); + return -EINVAL; + } + + if (*attach_type == BPF_FLOW_DISSECTOR) { + *mapfd = 0; + return 0; + } + + NEXT_ARG(); + if (!REQ_ARGS(2)) + return -EINVAL; + + *mapfd = map_parse_fd(&argc, &argv, 0); + if (*mapfd < 0) + return *mapfd; + + return 0; +} + +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, progfd; + int mapfd; + + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; + + err = bpf_prog_attach(progfd, mapfd, attach_type, 0); + if (err) { + p_err("failed prog attach to map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + return 0; +} + +static int do_detach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, progfd; + int mapfd; + + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; + + err = bpf_prog_detach2(progfd, mapfd, attach_type); + if (err) { + p_err("failed prog detach from map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + return 0; +} + +enum prog_tracelog_mode { + TRACE_STDOUT, + TRACE_STDERR, +}; + +static int +prog_tracelog_stream(int prog_fd, enum prog_tracelog_mode mode) +{ + FILE *file = mode == TRACE_STDOUT ? stdout : stderr; + int stream_id = mode == TRACE_STDOUT ? 1 : 2; + char buf[512]; + int ret; + + ret = 0; + do { + ret = bpf_prog_stream_read(prog_fd, stream_id, buf, sizeof(buf), NULL); + if (ret > 0) + fwrite(buf, sizeof(buf[0]), ret, file); + } while (ret > 0); + + fflush(file); + return ret ? -1 : 0; +} + +static int do_tracelog_any(int argc, char **argv) +{ + enum prog_tracelog_mode mode; + int fd; + + if (argc == 0) + return do_tracelog(argc, argv); + if (!is_prefix(*argv, "stdout") && !is_prefix(*argv, "stderr")) + usage(); + mode = is_prefix(*argv, "stdout") ? TRACE_STDOUT : TRACE_STDERR; + NEXT_ARG(); + + if (!REQ_ARGS(2)) + return -1; + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + return prog_tracelog_stream(fd, mode); +} + +static int check_single_stdin(char *file_data_in, char *file_ctx_in) +{ + if (file_data_in && file_ctx_in && + !strcmp(file_data_in, "-") && !strcmp(file_ctx_in, "-")) { + p_err("cannot use standard input for both data_in and ctx_in"); + return -1; + } + + return 0; +} + +static int get_run_data(const char *fname, void **data_ptr, unsigned int *size) +{ + size_t block_size = 256; + size_t buf_size = block_size; + size_t nb_read = 0; + void *tmp; + FILE *f; + + if (!fname) { + *data_ptr = NULL; + *size = 0; + return 0; + } + + if (!strcmp(fname, "-")) + f = stdin; + else + f = fopen(fname, "r"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + *data_ptr = malloc(block_size); + if (!*data_ptr) { + p_err("failed to allocate memory for data_in/ctx_in: %s", + strerror(errno)); + goto err_fclose; + } + + while ((nb_read += fread(*data_ptr + nb_read, 1, block_size, f))) { + if (feof(f)) + break; + if (ferror(f)) { + p_err("failed to read data_in/ctx_in from %s: %s", + fname, strerror(errno)); + goto err_free; + } + if (nb_read > buf_size - block_size) { + if (buf_size == UINT32_MAX) { + p_err("data_in/ctx_in is too long (max: %u)", + UINT32_MAX); + goto err_free; + } + /* No space for fread()-ing next chunk; realloc() */ + buf_size *= 2; + tmp = realloc(*data_ptr, buf_size); + if (!tmp) { + p_err("failed to reallocate data_in/ctx_in: %s", + strerror(errno)); + goto err_free; + } + *data_ptr = tmp; + } + } + if (f != stdin) + fclose(f); + + *size = nb_read; + return 0; + +err_free: + free(*data_ptr); + *data_ptr = NULL; +err_fclose: + if (f != stdin) + fclose(f); + return -1; +} + +static void hex_print(void *data, unsigned int size, FILE *f) +{ + size_t i, j; + char c; + + for (i = 0; i < size; i += 16) { + /* Row offset */ + fprintf(f, "%07zx\t", i); + + /* Hexadecimal values */ + for (j = i; j < i + 16 && j < size; j++) + fprintf(f, "%02x%s", *(uint8_t *)(data + j), + j % 2 ? " " : ""); + for (; j < i + 16; j++) + fprintf(f, " %s", j % 2 ? " " : ""); + + /* ASCII values (if relevant), '.' otherwise */ + fprintf(f, "| "); + for (j = i; j < i + 16 && j < size; j++) { + c = *(char *)(data + j); + if (c < ' ' || c > '~') + c = '.'; + fprintf(f, "%c%s", c, j == i + 7 ? " " : ""); + } + + fprintf(f, "\n"); + } +} + +static int +print_run_output(void *data, unsigned int size, const char *fname, + const char *json_key) +{ + size_t nb_written; + FILE *f; + + if (!fname) + return 0; + + if (!strcmp(fname, "-")) { + f = stdout; + if (json_output) { + jsonw_name(json_wtr, json_key); + print_data_json(data, size); + } else { + hex_print(data, size, f); + } + return 0; + } + + f = fopen(fname, "w"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + nb_written = fwrite(data, 1, size, f); + fclose(f); + if (nb_written != size) { + p_err("failed to write output data/ctx: %s", strerror(errno)); + return -1; + } + + return 0; +} + +static int alloc_run_data(void **data_ptr, unsigned int size_out) +{ + *data_ptr = calloc(size_out, 1); + if (!*data_ptr) { + p_err("failed to allocate memory for output data/ctx: %s", + strerror(errno)); + return -1; + } + + return 0; +} + +static int do_run(int argc, char **argv) +{ + char *data_fname_in = NULL, *data_fname_out = NULL; + char *ctx_fname_in = NULL, *ctx_fname_out = NULL; + const unsigned int default_size = SZ_32K; + void *data_in = NULL, *data_out = NULL; + void *ctx_in = NULL, *ctx_out = NULL; + unsigned int repeat = 1; + int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); + + if (!REQ_ARGS(4)) + return -1; + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + while (argc) { + if (detect_common_prefix(*argv, "data_in", "data_out", + "data_size_out", NULL)) + return -1; + if (detect_common_prefix(*argv, "ctx_in", "ctx_out", + "ctx_size_out", NULL)) + return -1; + + if (is_prefix(*argv, "data_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "data_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "data_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.data_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output data size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "ctx_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "ctx_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "ctx_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.ctx_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output context size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "repeat")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + repeat = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as repeat number", + *argv); + return -1; + } + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'data_in', 'data_out', 'data_size_out', 'ctx_in', 'ctx_out', 'ctx_size_out' or 'repeat', got: '%s'?", + *argv); + return -1; + } + } + + err = get_run_data(data_fname_in, &data_in, &test_attr.data_size_in); + if (err) + return -1; + + if (data_in) { + if (!test_attr.data_size_out) + test_attr.data_size_out = default_size; + err = alloc_run_data(&data_out, test_attr.data_size_out); + if (err) + goto free_data_in; + } + + err = get_run_data(ctx_fname_in, &ctx_in, &test_attr.ctx_size_in); + if (err) + goto free_data_out; + + if (ctx_in) { + if (!test_attr.ctx_size_out) + test_attr.ctx_size_out = default_size; + err = alloc_run_data(&ctx_out, test_attr.ctx_size_out); + if (err) + goto free_ctx_in; + } + + test_attr.repeat = repeat; + test_attr.data_in = data_in; + test_attr.data_out = data_out; + test_attr.ctx_in = ctx_in; + test_attr.ctx_out = ctx_out; + + err = bpf_prog_test_run_opts(fd, &test_attr); + if (err) { + p_err("failed to run program: %s", strerror(errno)); + goto free_ctx_out; + } + + err = 0; + + if (json_output) + jsonw_start_object(json_wtr); /* root */ + + /* Do not exit on errors occurring when printing output data/context, + * we still want to print return value and duration for program run. + */ + if (test_attr.data_size_out) + err += print_run_output(test_attr.data_out, + test_attr.data_size_out, + data_fname_out, "data_out"); + if (test_attr.ctx_size_out) + err += print_run_output(test_attr.ctx_out, + test_attr.ctx_size_out, + ctx_fname_out, "ctx_out"); + + if (json_output) { + jsonw_uint_field(json_wtr, "retval", test_attr.retval); + jsonw_uint_field(json_wtr, "duration", test_attr.duration); + jsonw_end_object(json_wtr); /* root */ + } else { + fprintf(stdout, "Return value: %u, duration%s: %uns\n", + test_attr.retval, + repeat > 1 ? " (average)" : "", test_attr.duration); + } + +free_ctx_out: + free(ctx_out); +free_ctx_in: + free(ctx_in); +free_data_out: + free(data_out); +free_data_in: + free(data_in); + + return err; +} + +static int +get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + libbpf_print_fn_t print_backup; + int ret; + + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + if (!ret) + return ret; + + /* libbpf_prog_type_by_name() failed, let's re-run with debug level */ + print_backup = libbpf_set_print(print_all_levels); + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + libbpf_set_print(print_backup); + + return ret; +} + +static int +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, + ); + 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; + const char *file; + int idx, err; + + + if (!REQ_ARGS(2)) + return -1; + file = GET_ARG(); + pinfile = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "type")) { + NEXT_ARG(); + + if (common_prog_type != BPF_PROG_TYPE_UNSPEC) { + p_err("program type already specified"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + err = libbpf_prog_type_by_name(*argv, &common_prog_type, + &expected_attach_type); + if (err < 0) { + /* Put a '/' at the end of type to appease libbpf */ + char *type = malloc(strlen(*argv) + 2); + + if (!type) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + *type = 0; + strcat(type, *argv); + strcat(type, "/"); + + err = get_prog_type_by_name(type, &common_prog_type, + &expected_attach_type); + free(type); + if (err < 0) + goto err_free_reuse_maps; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "map")) { + void *new_map_replace; + char *endptr, *name; + int fd; + + NEXT_ARG(); + + if (!REQ_ARGS(4)) + goto err_free_reuse_maps; + + if (is_prefix(*argv, "idx")) { + NEXT_ARG(); + + idx = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as IDX", *argv); + goto err_free_reuse_maps; + } + name = NULL; + } else if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + name = *argv; + idx = -1; + } else { + p_err("expected 'idx' or 'name', got: '%s'?", + *argv); + goto err_free_reuse_maps; + } + NEXT_ARG(); + + fd = map_parse_fd(&argc, &argv, 0); + if (fd < 0) + goto err_free_reuse_maps; + + new_map_replace = libbpf_reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); + if (!new_map_replace) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + map_replace = new_map_replace; + + map_replace[old_map_fds].idx = idx; + map_replace[old_map_fds].name = name; + map_replace[old_map_fds].fd = fd; + old_map_fds++; + } else if (is_prefix(*argv, "dev")) { + 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 (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; + + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "pinmaps")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + pinmaps = GET_ARG(); + } else if (is_prefix(*argv, "autoattach")) { + auto_attach = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "kernel_btf")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + open_opts.btf_custom_path = GET_ARG(); + } else { + p_err("expected no more arguments, " + "'type', 'map', 'offload_dev', 'xdpmeta_dev', 'pinmaps', " + "'autoattach', or 'kernel_btf', got: '%s'?", + *argv); + goto err_free_reuse_maps; + } + } + + set_max_rlimit(); + + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (!obj) { + p_err("failed to open object file"); + goto err_free_reuse_maps; + } + + bpf_object__for_each_program(pos, obj) { + enum bpf_prog_type prog_type = common_prog_type; + + if (prog_type == BPF_PROG_TYPE_UNSPEC) { + const char *sec_name = bpf_program__section_name(pos); + + err = get_prog_type_by_name(sec_name, &prog_type, + &expected_attach_type); + if (err < 0) + goto err_close_obj; + } + + 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); + } + + qsort(map_replace, old_map_fds, sizeof(*map_replace), + map_replace_compar); + + /* After the sort maps by name will be first on the list, because they + * have idx == -1. Resolve them. + */ + j = 0; + while (j < old_map_fds && map_replace[j].name) { + i = 0; + bpf_object__for_each_map(map, obj) { + if (!strcmp(bpf_map__name(map), map_replace[j].name)) { + map_replace[j].idx = i; + break; + } + i++; + } + if (map_replace[j].idx == -1) { + p_err("unable to find map '%s'", map_replace[j].name); + goto err_close_obj; + } + j++; + } + /* Resort if any names were resolved */ + if (j) + qsort(map_replace, old_map_fds, sizeof(*map_replace), + map_replace_compar); + + /* Set ifindex and name reuse */ + j = 0; + idx = 0; + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + bpf_map__set_ifindex(map, offload_ifindex); + + if (j < old_map_fds && idx == map_replace[j].idx) { + err = bpf_map__reuse_fd(map, map_replace[j++].fd); + if (err) { + p_err("unable to set up map reuse: %d", err); + goto err_close_obj; + } + + /* Next reuse wants to apply to the same map */ + if (j < old_map_fds && map_replace[j].idx == idx) { + p_err("replacement for map idx %d specified more than once", + idx); + goto err_close_obj; + } + } + + idx++; + } + if (j < old_map_fds) { + p_err("map idx '%d' not used", map_replace[j].idx); + goto err_close_obj; + } + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (first_prog_only) + err = mount_bpffs_for_file(pinfile); + else + err = create_and_mount_bpffs_dir(pinfile); + if (err) + goto err_close_obj; + + if (first_prog_only) { + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + p_err("object file doesn't contain any bpf program"); + goto err_close_obj; + } + + 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__section_name(prog)); + goto err_close_obj; + } + } else { + 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; + } + } + + if (pinmaps) { + err = create_and_mount_bpffs_dir(pinmaps); + if (err) + goto err_unpin; + + err = bpf_object__pin_maps(obj, pinmaps); + if (err) { + p_err("failed to pin all maps"); + goto err_unpin; + } + } + + if (json_output) + jsonw_null(json_wtr); + + bpf_object__close(obj); + for (i = 0; i < old_map_fds; i++) + close(map_replace[i].fd); + free(map_replace); + + return 0; + +err_unpin: + if (first_prog_only) + unlink(pinfile); + else + bpf_object__unpin_programs(obj, pinfile); +err_close_obj: + bpf_object__close(obj); +err_free_reuse_maps: + for (i = 0; i < old_map_fds; i++) + close(map_replace[i].fd); + free(map_replace); + return -1; +} + +static int count_open_fds(void) +{ + DIR *dp = opendir("/proc/self/fd"); + struct dirent *de; + int cnt = -3; + + if (!dp) + return -1; + + while ((de = readdir(dp))) + cnt++; + + closedir(dp); + return cnt; +} + +static int try_loader(struct gen_loader_opts *gen) +{ + struct bpf_load_and_run_opts opts = {}; + struct bpf_loader_ctx *ctx; + char sig_buf[MAX_SIG_SIZE]; + __u8 prog_sha[SHA256_DIGEST_LENGTH]; + 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(); + + if (sign_progs) { + opts.excl_prog_hash = prog_sha; + opts.excl_prog_hash_sz = sizeof(prog_sha); + opts.signature = sig_buf; + opts.signature_sz = MAX_SIG_SIZE; + opts.keyring_id = KEY_SPEC_SESSION_KEYRING; + + err = bpftool_prog_sign(&opts); + if (err < 0) { + p_err("failed to sign program"); + goto out; + } + + err = register_session_key(cert_path); + if (err < 0) { + p_err("failed to add session key"); + goto out; + } + } + 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); + } +out: + 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) { + err = -1; + p_err("failed to open object file"); + goto err_close_obj; + } + + if (sign_progs) + gen.gen_hash = true; + + err = bpf_object__gen_loader(obj, &gen); + if (err) + goto err_close_obj; + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (verifier_logs) { + struct dump_data dd = {}; + + kernel_syms_load(&dd); + dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false); + kernel_syms_destroy(&dd); + } + err = try_loader(&gen); +err_close_obj: + bpf_object__close(obj); + return err; +} + +static int do_load(int argc, char **argv) +{ + if (use_loader) + return do_loader(argc, argv); + return load_with_options(argc, argv, true); +} + +static int do_loadall(int argc, char **argv) +{ + return load_with_options(argc, argv, false); +} + +#ifdef BPFTOOL_WITHOUT_SKELETONS + +static int do_profile(int argc, char **argv) +{ + p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0"); + return 0; +} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "profiler.skel.h" + +struct profile_metric { + const char *name; + struct bpf_perf_event_value val; + struct perf_event_attr attr; + bool selected; + + /* calculate ratios like instructions per cycle */ + const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */ + const char *ratio_desc; + const float ratio_mul; +} metrics[] = { + { + .name = "cycles", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .exclude_user = 1, + }, + }, + { + .name = "instructions", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .exclude_user = 1, + }, + .ratio_metric = 1, + .ratio_desc = "insns per cycle", + .ratio_mul = 1.0, + }, + { + .name = "l1d_loads", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), + .exclude_user = 1, + }, + }, + { + .name = "llc_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_LL | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "LLC misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "itlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "itlb misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "dtlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "dtlb misses per million insns", + .ratio_mul = 1e6, + }, +}; + +static __u64 profile_total_count; + +#define MAX_NUM_PROFILE_METRICS 4 + +static int profile_parse_metrics(int argc, char **argv) +{ + unsigned int metric_cnt; + int selected_cnt = 0; + unsigned int i; + + metric_cnt = ARRAY_SIZE(metrics); + + while (argc > 0) { + for (i = 0; i < metric_cnt; i++) { + if (is_prefix(argv[0], metrics[i].name)) { + if (!metrics[i].selected) + selected_cnt++; + metrics[i].selected = true; + break; + } + } + if (i == metric_cnt) { + p_err("unknown metric %s", argv[0]); + return -1; + } + NEXT_ARG(); + } + if (selected_cnt > MAX_NUM_PROFILE_METRICS) { + p_err("too many (%d) metrics, please specify no more than %d metrics at a time", + selected_cnt, MAX_NUM_PROFILE_METRICS); + return -1; + } + return selected_cnt; +} + +static void profile_read_values(struct profiler_bpf *obj) +{ + __u32 m, cpu, num_cpu = obj->rodata->num_cpu; + int reading_map_fd, count_map_fd; + __u64 counts[num_cpu]; + __u32 key = 0; + int err; + + reading_map_fd = bpf_map__fd(obj->maps.accum_readings); + count_map_fd = bpf_map__fd(obj->maps.counts); + if (reading_map_fd < 0 || count_map_fd < 0) { + p_err("failed to get fd for map"); + return; + } + + err = bpf_map_lookup_elem(count_map_fd, &key, counts); + if (err) { + p_err("failed to read count_map: %s", strerror(errno)); + return; + } + + profile_total_count = 0; + for (cpu = 0; cpu < num_cpu; cpu++) + profile_total_count += counts[cpu]; + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value values[num_cpu]; + + if (!metrics[m].selected) + continue; + + err = bpf_map_lookup_elem(reading_map_fd, &key, values); + if (err) { + p_err("failed to read reading_map: %s", + strerror(errno)); + return; + } + for (cpu = 0; cpu < num_cpu; cpu++) { + metrics[m].val.counter += values[cpu].counter; + metrics[m].val.enabled += values[cpu].enabled; + metrics[m].val.running += values[cpu].running; + } + key++; + } +} + +static void profile_print_readings_json(void) +{ + __u32 m; + + jsonw_start_array(json_wtr); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "metric", metrics[m].name); + jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count); + jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter); + jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled); + jsonw_lluint_field(json_wtr, "running", metrics[m].val.running); + + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +static void profile_print_readings_plain(void) +{ + __u32 m; + + printf("\n%18llu %-20s\n", profile_total_count, "run_cnt"); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value *val = &metrics[m].val; + int r; + + if (!metrics[m].selected) + continue; + printf("%18llu %-20s", val->counter, metrics[m].name); + + r = metrics[m].ratio_metric - 1; + if (r >= 0 && metrics[r].selected && + metrics[r].val.counter > 0) { + printf("# %8.2f %-30s", + val->counter * metrics[m].ratio_mul / + metrics[r].val.counter, + metrics[m].ratio_desc); + } else { + printf("%-41s", ""); + } + + if (val->enabled > val->running) + printf("(%4.2f%%)", + val->running * 100.0 / val->enabled); + printf("\n"); + } +} + +static void profile_print_readings(void) +{ + if (json_output) + profile_print_readings_json(); + else + profile_print_readings_plain(); +} + +static char *profile_target_name(int tgt_fd) +{ + struct bpf_func_info func_info = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const struct btf_type *t; + __u32 func_info_rec_size; + struct btf *btf = NULL; + char *name = NULL; + int err; + + err = bpf_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.btf_id == 0) { + p_err("prog FD %d doesn't have valid btf", tgt_fd); + goto out; + } + + func_info_rec_size = info.func_info_rec_size; + if (info.nr_func_info == 0) { + p_err("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 %u doesn't have type %u", + info.btf_id, func_info.type_id); + goto out; + } + name = strdup(btf__name_by_offset(btf, t->name_off)); +out: + btf__free(btf); + return name; +} + +static struct profiler_bpf *profile_obj; +static int profile_tgt_fd = -1; +static char *profile_tgt_name; +static int *profile_perf_events; +static int profile_perf_event_cnt; + +static void profile_close_perf_events(struct profiler_bpf *obj) +{ + int i; + + for (i = profile_perf_event_cnt - 1; i >= 0; i--) + close(profile_perf_events[i]); + + free(profile_perf_events); + profile_perf_event_cnt = 0; +} + +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + +static int profile_open_perf_events(struct profiler_bpf *obj) +{ + unsigned int cpu, m; + int map_fd; + + profile_perf_events = calloc( + 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)); + return -1; + } + map_fd = bpf_map__fd(obj->maps.events); + if (map_fd < 0) { + p_err("failed to get fd for events map"); + return -1; + } + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { + if (profile_open_perf_event(m, cpu, map_fd)) { + p_err("failed to create event %s on cpu %u", + metrics[m].name, cpu); + return -1; + } + } + } + return 0; +} + +static void profile_print_and_cleanup(void) +{ + profile_close_perf_events(profile_obj); + profile_read_values(profile_obj); + profile_print_readings(); + profiler_bpf__destroy(profile_obj); + + close(profile_tgt_fd); + free(profile_tgt_name); +} + +static void int_exit(int signo) +{ + profile_print_and_cleanup(); + exit(0); +} + +static int do_profile(int argc, char **argv) +{ + int num_metric, num_cpu, err = -1; + struct bpf_program *prog; + unsigned long duration; + char *endptr; + + /* we at least need two args for the prog and one metric */ + if (!REQ_ARGS(3)) + return -EINVAL; + + /* parse target fd */ + profile_tgt_fd = prog_parse_fd(&argc, &argv); + if (profile_tgt_fd < 0) { + p_err("failed to parse fd"); + return -1; + } + + /* parse profiling optional duration */ + if (argc > 2 && is_prefix(argv[0], "duration")) { + NEXT_ARG(); + duration = strtoul(*argv, &endptr, 0); + if (*endptr) + usage(); + NEXT_ARG(); + } else { + duration = UINT_MAX; + } + + num_metric = profile_parse_metrics(argc, argv); + if (num_metric <= 0) + goto out; + + num_cpu = libbpf_num_possible_cpus(); + if (num_cpu <= 0) { + p_err("failed to identify number of CPUs"); + goto out; + } + + profile_obj = profiler_bpf__open(); + if (!profile_obj) { + p_err("failed to open and/or load BPF object"); + goto out; + } + + profile_obj->rodata->num_cpu = num_cpu; + profile_obj->rodata->num_metric = num_metric; + + /* adjust map sizes */ + bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.counts, 1); + + /* change target name */ + profile_tgt_name = profile_target_name(profile_tgt_fd); + if (!profile_tgt_name) + goto out; + + bpf_object__for_each_program(prog, profile_obj->obj) { + err = bpf_program__set_attach_target(prog, profile_tgt_fd, + profile_tgt_name); + if (err) { + p_err("failed to set attach target\n"); + goto out; + } + } + + set_max_rlimit(); + err = profiler_bpf__load(profile_obj); + if (err) { + p_err("failed to load profile_obj"); + goto out; + } + + err = profile_open_perf_events(profile_obj); + if (err) + goto out; + + err = profiler_bpf__attach(profile_obj); + if (err) { + p_err("failed to attach profile_obj"); + goto out; + } + signal(SIGINT, int_exit); + + sleep(duration); + profile_print_and_cleanup(); + return 0; + +out: + profile_close_perf_events(profile_obj); + if (profile_obj) + profiler_bpf__destroy(profile_obj); + close(profile_tgt_fd); + free(profile_tgt_name); + return err; +} + +#endif /* BPFTOOL_WITHOUT_SKELETONS */ + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [PROG]\n" + " %1$s %2$s dump xlated PROG [{ file FILE | [opcodes] [linum] [visual] }]\n" + " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" + " %1$s %2$s pin PROG FILE\n" + " %1$s %2$s { load | loadall } OBJ PATH \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" + " [map { idx IDX | name NAME } MAP]\\\n" + " [pinmaps MAP_DIR]\n" + " [autoattach]\n" + " [kernel_btf BTF_FILE]\n" + " %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$s run PROG \\\n" + " data_in FILE \\\n" + " [data_out FILE [data_size_out L]] \\\n" + " [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n" + " [repeat N]\n" + " %1$s %2$s profile PROG [duration DURATION] METRICs\n" + " %1$s %2$s tracelog\n" + " %1$s %2$s tracelog { stdout | stderr } PROG\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " TYPE := { socket | kprobe | kretprobe | classifier | action |\n" + " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n" + " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n" + " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n" + " sk_reuseport | flow_dissector | cgroup/sysctl |\n" + " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" + " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" + " cgroup/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 | fsession | 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} | [ {-S|--sign } {-k} <private_key.pem> {-i} <certificate.x509> ] \n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { "pin", do_pin }, + { "load", do_load }, + { "loadall", do_loadall }, + { "attach", do_attach }, + { "detach", do_detach }, + { "tracelog", do_tracelog_any }, + { "run", do_run }, + { "profile", do_profile }, + { 0 } +}; + +int do_prog(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/sign.c b/tools/bpf/bpftool/sign.c new file mode 100644 index 000000000..f9b742f4b --- /dev/null +++ b/tools/bpf/bpftool/sign.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) 2025 Google LLC. + */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <stdbool.h> +#include <string.h> +#include <getopt.h> +#include <err.h> +#include <openssl/opensslv.h> +#include <openssl/bio.h> +#include <openssl/evp.h> +#include <openssl/pem.h> +#include <openssl/err.h> +#include <openssl/cms.h> +#include <linux/keyctl.h> +#include <errno.h> + +#include <bpf/skel_internal.h> + +#include "main.h" + +#define OPEN_SSL_ERR_BUF_LEN 256 + +/* Use deprecated in 3.0 ERR_get_error_line_data for openssl < 3 */ +#if !defined(OPENSSL_VERSION_MAJOR) || (OPENSSL_VERSION_MAJOR < 3) +#define ERR_get_error_all(file, line, func, data, flags) \ + ERR_get_error_line_data(file, line, data, flags) +#endif + +static void display_openssl_errors(int l) +{ + char buf[OPEN_SSL_ERR_BUF_LEN]; + const char *file; + const char *data; + unsigned long e; + int flags; + int line; + + while ((e = ERR_get_error_all(&file, &line, NULL, &data, &flags))) { + ERR_error_string_n(e, buf, sizeof(buf)); + if (data && (flags & ERR_TXT_STRING)) { + p_err("OpenSSL %s: %s:%d: %s", buf, file, line, data); + } else { + p_err("OpenSSL %s: %s:%d", buf, file, line); + } + } +} + +#define DISPLAY_OSSL_ERR(cond) \ + do { \ + bool __cond = (cond); \ + if (__cond && ERR_peek_error()) \ + display_openssl_errors(__LINE__);\ + } while (0) + +static EVP_PKEY *read_private_key(const char *pkey_path) +{ + EVP_PKEY *private_key = NULL; + BIO *b; + + b = BIO_new_file(pkey_path, "rb"); + private_key = PEM_read_bio_PrivateKey(b, NULL, NULL, NULL); + BIO_free(b); + DISPLAY_OSSL_ERR(!private_key); + return private_key; +} + +static X509 *read_x509(const char *x509_name) +{ + unsigned char buf[2]; + X509 *x509 = NULL; + BIO *b; + int n; + + b = BIO_new_file(x509_name, "rb"); + if (!b) + goto cleanup; + + /* Look at the first two bytes of the file to determine the encoding */ + n = BIO_read(b, buf, 2); + if (n != 2) + goto cleanup; + + if (BIO_reset(b) != 0) + goto cleanup; + + if (buf[0] == 0x30 && buf[1] >= 0x81 && buf[1] <= 0x84) + /* Assume raw DER encoded X.509 */ + x509 = d2i_X509_bio(b, NULL); + else + /* Assume PEM encoded X.509 */ + x509 = PEM_read_bio_X509(b, NULL, NULL, NULL); + +cleanup: + BIO_free(b); + DISPLAY_OSSL_ERR(!x509); + return x509; +} + +__u32 register_session_key(const char *key_der_path) +{ + unsigned char *der_buf = NULL; + X509 *x509 = NULL; + int key_id = -1; + int der_len; + + if (!key_der_path) + return key_id; + x509 = read_x509(key_der_path); + if (!x509) + goto cleanup; + der_len = i2d_X509(x509, &der_buf); + if (der_len < 0) + goto cleanup; + key_id = syscall(__NR_add_key, "asymmetric", key_der_path, der_buf, + (size_t)der_len, KEY_SPEC_SESSION_KEYRING); +cleanup: + X509_free(x509); + OPENSSL_free(der_buf); + DISPLAY_OSSL_ERR(key_id == -1); + return key_id; +} + +int bpftool_prog_sign(struct bpf_load_and_run_opts *opts) +{ + BIO *bd_in = NULL, *bd_out = NULL; + EVP_PKEY *private_key = NULL; + CMS_ContentInfo *cms = NULL; + long actual_sig_len = 0; + X509 *x509 = NULL; + int err = 0; + + bd_in = BIO_new_mem_buf(opts->insns, opts->insns_sz); + if (!bd_in) { + err = -ENOMEM; + goto cleanup; + } + + private_key = read_private_key(private_key_path); + if (!private_key) { + err = -EINVAL; + goto cleanup; + } + + x509 = read_x509(cert_path); + if (!x509) { + err = -EINVAL; + goto cleanup; + } + + cms = CMS_sign(NULL, NULL, NULL, NULL, + CMS_NOCERTS | CMS_PARTIAL | CMS_BINARY | CMS_DETACHED | + CMS_STREAM); + if (!cms) { + err = -EINVAL; + goto cleanup; + } + + if (!CMS_add1_signer(cms, x509, private_key, EVP_sha256(), + CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP | + CMS_USE_KEYID | CMS_NOATTR)) { + err = -EINVAL; + goto cleanup; + } + + if (CMS_final(cms, bd_in, NULL, CMS_NOCERTS | CMS_BINARY) != 1) { + err = -EIO; + goto cleanup; + } + + EVP_Digest(opts->insns, opts->insns_sz, opts->excl_prog_hash, + &opts->excl_prog_hash_sz, EVP_sha256(), NULL); + + bd_out = BIO_new(BIO_s_mem()); + if (!bd_out) { + err = -ENOMEM; + goto cleanup; + } + + if (!i2d_CMS_bio_stream(bd_out, cms, NULL, 0)) { + err = -EIO; + goto cleanup; + } + + actual_sig_len = BIO_get_mem_data(bd_out, NULL); + if (actual_sig_len <= 0) { + err = -EIO; + goto cleanup; + } + + if ((size_t)actual_sig_len > opts->signature_sz) { + err = -ENOSPC; + goto cleanup; + } + + if (BIO_read(bd_out, opts->signature, actual_sig_len) != actual_sig_len) { + err = -EIO; + goto cleanup; + } + + opts->signature_sz = actual_sig_len; +cleanup: + BIO_free(bd_out); + CMS_ContentInfo_free(cms); + X509_free(x509); + EVP_PKEY_free(private_key); + BIO_free(bd_in); + DISPLAY_OSSL_ERR(err < 0); + return err; +} diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c new file mode 100644 index 000000000..948dde250 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -0,0 +1,124 @@ +// 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_link_fops_poll __ksym __weak; +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: + if (&bpf_link_fops_poll && + file->f_op == &bpf_link_fops_poll) + fops = &bpf_link_fops_poll; + else + 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 (BPF_CORE_READ(link, type) == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), + task->group_leader->comm); + bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h new file mode 100644 index 000000000..bbb570d4c --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (c) 2020 Facebook */ +#ifndef __PID_ITER_H +#define __PID_ITER_H + +struct pid_iter_entry { + __u32 id; + int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; + char comm[16]; +}; + +#endif diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c new file mode 100644 index 000000000..f48c783cb --- /dev/null +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2020 Facebook +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + +/* map of perf event fds, num_cpu * num_metric entries */ +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(int)); +} events SEC(".maps"); + +/* readings at fentry */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); +} fentry_readings SEC(".maps"); + +/* accumulated readings */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); +} accum_readings SEC(".maps"); + +/* sample counts, one per cpu */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u64)); +} counts SEC(".maps"); + +const volatile __u32 num_cpu = 1; +const volatile __u32 num_metric = 1; +#define MAX_NUM_METRICS 4 + +SEC("fentry/XXX") +int BPF_PROG(fentry_XXX) +{ + struct bpf_perf_event_value___local *ptrs[MAX_NUM_METRICS]; + u32 key = bpf_get_smp_processor_id(); + u32 i; + + /* look up before reading, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { + u32 flag = i; + + ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag); + if (!ptrs[i]) + return 0; + } + + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { + struct bpf_perf_event_value___local reading; + int err; + + err = bpf_perf_event_read_value(&events, key, (void *)&reading, + sizeof(reading)); + if (err) + return 0; + *(ptrs[i]) = reading; + key += num_cpu; + } + + return 0; +} + +static inline void +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) +{ + struct bpf_perf_event_value___local *before, diff; + + before = bpf_map_lookup_elem(&fentry_readings, &id); + /* only account samples with a valid fentry_reading */ + if (before && before->counter) { + struct bpf_perf_event_value___local *accum; + + diff.counter = after->counter - before->counter; + diff.enabled = after->enabled - before->enabled; + diff.running = after->running - before->running; + + accum = bpf_map_lookup_elem(&accum_readings, &id); + if (accum) { + accum->counter += diff.counter; + accum->enabled += diff.enabled; + accum->running += diff.running; + } + } +} + +SEC("fexit/XXX") +int BPF_PROG(fexit_XXX) +{ + struct bpf_perf_event_value___local readings[MAX_NUM_METRICS]; + u32 cpu = bpf_get_smp_processor_id(); + u32 i, zero = 0; + int err; + u64 *count; + + /* read all events before updating the maps, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { + err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, + (void *)(readings + i), + sizeof(*readings)); + if (err) + return 0; + } + count = bpf_map_lookup_elem(&counts, &zero); + if (count) { + *count += 1; + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) + fexit_update_maps(i, &readings[i]); + } + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c new file mode 100644 index 000000000..aa43dead2 --- /dev/null +++ b/tools/bpf/bpftool/struct_ops.c @@ -0,0 +1,648 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <stdio.h> +#include <unistd.h> + +#include <linux/err.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> + +#include "json_writer.h" +#include "main.h" + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" + +static const struct btf_type *map_info_type; +static __u32 map_info_alloc_len; +static struct btf *btf_vmlinux; +static __s32 map_info_type_id; + +struct res { + unsigned int nr_maps; + unsigned int nr_errs; +}; + +static const struct btf *get_btf_vmlinux(void) +{ + if (btf_vmlinux) + return btf_vmlinux; + + btf_vmlinux = libbpf_find_kernel_btf(); + if (!btf_vmlinux) + p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); + + return btf_vmlinux; +} + +static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) +{ + const struct btf *kern_btf; + const struct btf_type *t; + const char *st_ops_name; + + kern_btf = get_btf_vmlinux(); + if (!kern_btf) + return "<btf_vmlinux_not_found>"; + + t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); + st_ops_name = btf__name_by_offset(kern_btf, t->name_off); + st_ops_name += strlen(STRUCT_OPS_VALUE_PREFIX); + + return st_ops_name; +} + +static __s32 get_map_info_type_id(void) +{ + const struct btf *kern_btf; + + if (map_info_type_id) + return map_info_type_id; + + kern_btf = get_btf_vmlinux(); + if (!kern_btf) + return 0; + + map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info", + BTF_KIND_STRUCT); + if (map_info_type_id < 0) { + p_err("can't find bpf_map_info from btf_vmlinux"); + return map_info_type_id; + } + map_info_type = btf__type_by_id(kern_btf, map_info_type_id); + + /* Ensure map_info_alloc() has at least what the bpftool needs */ + map_info_alloc_len = map_info_type->size; + if (map_info_alloc_len < sizeof(struct bpf_map_info)) + map_info_alloc_len = sizeof(struct bpf_map_info); + + return map_info_type_id; +} + +/* If the subcmd needs to print out the bpf_map_info, + * it should always call map_info_alloc to allocate + * a bpf_map_info object instead of allocating it + * on the stack. + * + * map_info_alloc() will take the running kernel's btf + * into account. i.e. it will consider the + * sizeof(struct bpf_map_info) of the running kernel. + * + * It will enable the "struct_ops" cmd to print the latest + * "struct bpf_map_info". + * + * [ Recall that "struct_ops" requires the kernel's btf to + * be available ] + */ +static struct bpf_map_info *map_info_alloc(__u32 *alloc_len) +{ + struct bpf_map_info *info; + + if (get_map_info_type_id() < 0) + return NULL; + + info = calloc(1, map_info_alloc_len); + if (!info) + p_err("mem alloc failed"); + else + *alloc_len = map_info_alloc_len; + + return info; +} + +/* It iterates all struct_ops maps of the system. + * It returns the fd in "*res_fd" and map_info in "*info". + * In the very first iteration, info->id should be 0. + * An optional map "*name" filter can be specified. + * The filter can be made more flexible in the future. + * e.g. filter by kernel-struct-ops-name, regex-name, glob-name, ...etc. + * + * Return value: + * 1: A struct_ops map found. It is returned in "*res_fd" and "*info". + * The caller can continue to call get_next in the future. + * 0: No struct_ops map is returned. + * All struct_ops map has been found. + * -1: Error and the caller should abort the iteration. + */ +static int get_next_struct_ops_map(const char *name, int *res_fd, + struct bpf_map_info *info, __u32 info_len) +{ + __u32 id = info->id; + int err, fd; + + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + return 0; + p_err("can't get next map: %s", strerror(errno)); + return -1; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + return -1; + } + + err = bpf_map_get_info_by_fd(fd, info, &info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return -1; + } + + if (info->type == BPF_MAP_TYPE_STRUCT_OPS && + (!name || !strcmp(name, info->name))) { + *res_fd = fd; + return 1; + } + close(fd); + } +} + +static int cmd_retval(const struct res *res, bool must_have_one_map) +{ + if (res->nr_errs || (!res->nr_maps && must_have_one_map)) + return -1; + + return 0; +} + +/* "data" is the work_func private storage */ +typedef int (*work_func)(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr); + +/* Find all struct_ops map in the system. + * Filter out by "name" (if specified). + * Then call "func(fd, info, data, wtr)" on each struct_ops map found. + */ +static struct res do_search(const char *name, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + __u32 info_len; + int fd, err; + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + return res; + } + + if (wtr) + jsonw_start_array(wtr); + while ((err = get_next_struct_ops_map(name, &fd, info, info_len)) == 1) { + res.nr_maps++; + err = func(fd, info, data, wtr); + if (err) + res.nr_errs++; + close(fd); + } + if (wtr) + jsonw_end_array(wtr); + + if (err) + res.nr_errs++; + + if (!wtr && name && !res.nr_errs && !res.nr_maps) + /* It is not printing empty []. + * Thus, needs to specifically say nothing found + * for "name" here. + */ + p_err("no struct_ops found for %s", name); + else if (!wtr && json_output && !res.nr_errs) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + + free(info); + return res; +} + +static struct res do_one_id(const char *id_str, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + unsigned long id; + __u32 info_len; + char *endptr; + int fd; + + id = strtoul(id_str, &endptr, 0); + if (*endptr || !id || id > UINT32_MAX) { + p_err("invalid id %s", id_str); + res.nr_errs++; + return res; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%lu): %s", id, strerror(errno)); + res.nr_errs++; + return res; + } + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + goto done; + } + + if (bpf_map_get_info_by_fd(fd, info, &info_len)) { + p_err("can't get map info: %s", strerror(errno)); + res.nr_errs++; + goto done; + } + + if (info->type != BPF_MAP_TYPE_STRUCT_OPS) { + p_err("%s id %u is not a struct_ops map", info->name, info->id); + res.nr_errs++; + goto done; + } + + res.nr_maps++; + + if (wtr) + jsonw_start_array(wtr); + + if (func(fd, info, data, wtr)) + res.nr_errs++; + else if (!wtr && json_output) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + + if (wtr) + jsonw_end_array(wtr); + +done: + free(info); + close(fd); + + return res; +} + +static struct res do_work_on_struct_ops(const char *search_type, + const char *search_term, + work_func func, void *data, + struct json_writer *wtr) +{ + if (search_type) { + if (is_prefix(search_type, "id")) + return do_one_id(search_term, func, data, wtr); + else if (!is_prefix(search_type, "name")) + usage(); + } + + return do_search(search_term, func, data, wtr); +} + +static int __do_show(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + if (wtr) { + jsonw_start_object(wtr); + jsonw_uint_field(wtr, "id", info->id); + jsonw_string_field(wtr, "name", info->name); + jsonw_string_field(wtr, "kernel_struct_ops", + get_kern_struct_ops_name(info)); + jsonw_end_object(wtr); + } else { + printf("%u: %-15s %-32s\n", info->id, info->name, + get_kern_struct_ops_name(info)); + } + + return 0; +} + +static int do_show(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + res = do_work_on_struct_ops(search_type, search_term, __do_show, + NULL, json_wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_dump(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + struct btf_dumper *d = (struct btf_dumper *)data; + const struct btf_type *struct_ops_type; + const struct btf *kern_btf = d->btf; + const char *struct_ops_name; + int zero = 0; + void *value; + + /* note: d->jw == wtr */ + + kern_btf = d->btf; + + /* The kernel supporting BPF_MAP_TYPE_STRUCT_OPS must have + * btf_vmlinux_value_type_id. + */ + struct_ops_type = btf__type_by_id(kern_btf, + info->btf_vmlinux_value_type_id); + struct_ops_name = btf__name_by_offset(kern_btf, + struct_ops_type->name_off); + value = calloc(1, info->value_size); + if (!value) { + p_err("mem alloc failed"); + return -1; + } + + if (bpf_map_lookup_elem(fd, &zero, value)) { + p_err("can't lookup struct_ops map %s id %u", + info->name, info->id); + free(value); + return -1; + } + + jsonw_start_object(wtr); + jsonw_name(wtr, "bpf_map_info"); + btf_dumper_type(d, map_info_type_id, (void *)info); + jsonw_end_object(wtr); + + jsonw_start_object(wtr); + jsonw_name(wtr, struct_ops_name); + btf_dumper_type(d, info->btf_vmlinux_value_type_id, value); + jsonw_end_object(wtr); + + free(value); + + return 0; +} + +static int do_dump(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + json_writer_t *wtr = json_wtr; + const struct btf *kern_btf; + struct btf_dumper d = {}; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + kern_btf = get_btf_vmlinux(); + if (!kern_btf) + return -1; + + if (!json_output) { + wtr = jsonw_new(stdout); + if (!wtr) { + p_err("can't create json writer"); + return -1; + } + jsonw_pretty(wtr, true); + } + + d.btf = kern_btf; + d.jw = wtr; + d.is_plain_text = !json_output; + d.prog_id_as_func_ptr = true; + + res = do_work_on_struct_ops(search_type, search_term, __do_dump, &d, + wtr); + + if (!json_output) + jsonw_destroy(&wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_unregister(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + int zero = 0; + + if (bpf_map_delete_elem(fd, &zero)) { + p_err("can't unload %s %s id %u: %s", + get_kern_struct_ops_name(info), info->name, + info->id, strerror(errno)); + return -1; + } + + p_info("Unregistered %s %s id %u", + get_kern_struct_ops_name(info), info->name, + info->id); + + return 0; +} + +static int do_unregister(int argc, char **argv) +{ + const char *search_type, *search_term; + struct res res; + + if (argc != 2) + usage(); + + search_type = GET_ARG(); + search_term = GET_ARG(); + + res = do_work_on_struct_ops(search_type, search_term, + __do_unregister, NULL, NULL); + + return cmd_retval(&res, true); +} + +static int 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) +{ + 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 && argc != 2) + usage(); + + file = GET_ARG(); + if (argc == 1) + linkdir = GET_ARG(); + + if (linkdir && create_and_mount_bpffs_dir(linkdir)) { + p_err("can't mount bpffs for pinning"); + return -1; + } + + 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) + return -1; + + set_max_rlimit(); + + if (bpf_object__load(obj)) { + bpf_object__close(obj); + return -1; + } + + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + + link = bpf_map__attach_struct_ops(map); + if (!link) { + p_err("can't register struct_ops %s: %s", + bpf_map__name(map), strerror(errno)); + nr_errs++; + continue; + } + nr_maps++; + + 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); + + if (nr_errs) + return -1; + + if (!nr_maps) { + p_err("no struct_ops found in %s", file); + return -1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [STRUCT_OPS_MAP]\n" + " %1$s %2$s dump [STRUCT_OPS_MAP]\n" + " %1$s %2$s register OBJ [LINK_DIR]\n" + " %1$s %2$s unregister STRUCT_OPS_MAP\n" + " %1$s %2$s help\n" + "\n" + " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "register", do_register }, + { "unregister", do_unregister }, + { "dump", do_dump }, + { "help", do_help }, + { 0 } +}; + +int do_struct_ops(int argc, char **argv) +{ + int err; + + err = cmd_select(cmds, argc, argv, do_help); + + btf__free(btf_vmlinux); + + return err; +} diff --git a/tools/bpf/bpftool/token.c b/tools/bpf/bpftool/token.c new file mode 100644 index 000000000..c08f34b9d --- /dev/null +++ b/tools/bpf/bpftool/token.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2025 Didi Technology Co., Tao Chen */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <mntent.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "json_writer.h" +#include "main.h" + +#define MOUNTS_FILE "/proc/mounts" + +static struct { + const char *header; + const char *key; +} sets[] = { + {"allowed_cmds", "delegate_cmds"}, + {"allowed_maps", "delegate_maps"}, + {"allowed_progs", "delegate_progs"}, + {"allowed_attachs", "delegate_attachs"}, +}; + +static bool has_delegate_options(const char *mnt_ops) +{ + return strstr(mnt_ops, "delegate_cmds") || + strstr(mnt_ops, "delegate_maps") || + strstr(mnt_ops, "delegate_progs") || + strstr(mnt_ops, "delegate_attachs"); +} + +static char *get_delegate_value(char *opts, const char *key) +{ + char *token, *rest, *ret = NULL; + + if (!opts) + return NULL; + + for (token = strtok_r(opts, ",", &rest); token; + token = strtok_r(NULL, ",", &rest)) { + if (strncmp(token, key, strlen(key)) == 0 && + token[strlen(key)] == '=') { + ret = token + strlen(key) + 1; + break; + } + } + + return ret; +} + +static void print_items_per_line(char *input, int items_per_line) +{ + char *str, *rest; + int cnt = 0; + + if (!input) + return; + + for (str = strtok_r(input, ":", &rest); str; + str = strtok_r(NULL, ":", &rest)) { + if (cnt % items_per_line == 0) + printf("\n\t "); + + printf("%-20s", str); + cnt++; + } +} + +#define ITEMS_PER_LINE 4 +static void show_token_info_plain(struct mntent *mntent) +{ + size_t i; + + printf("token_info %s", mntent->mnt_dir); + + for (i = 0; i < ARRAY_SIZE(sets); i++) { + char *opts, *value; + + printf("\n\t%s:", sets[i].header); + opts = strdup(mntent->mnt_opts); + value = get_delegate_value(opts, sets[i].key); + print_items_per_line(value, ITEMS_PER_LINE); + free(opts); + } + + printf("\n"); +} + +static void split_json_array_str(char *input) +{ + char *str, *rest; + + if (!input) { + jsonw_start_array(json_wtr); + jsonw_end_array(json_wtr); + return; + } + + jsonw_start_array(json_wtr); + for (str = strtok_r(input, ":", &rest); str; + str = strtok_r(NULL, ":", &rest)) { + jsonw_string(json_wtr, str); + } + jsonw_end_array(json_wtr); +} + +static void show_token_info_json(struct mntent *mntent) +{ + size_t i; + + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "token_info", mntent->mnt_dir); + + for (i = 0; i < ARRAY_SIZE(sets); i++) { + char *opts, *value; + + jsonw_name(json_wtr, sets[i].header); + opts = strdup(mntent->mnt_opts); + value = get_delegate_value(opts, sets[i].key); + split_json_array_str(value); + free(opts); + } + + jsonw_end_object(json_wtr); +} + +static int __show_token_info(struct mntent *mntent) +{ + if (json_output) + show_token_info_json(mntent); + else + show_token_info_plain(mntent); + + return 0; +} + +static int show_token_info(void) +{ + FILE *fp; + struct mntent *ent; + + fp = setmntent(MOUNTS_FILE, "r"); + if (!fp) { + p_err("Failed to open: %s", MOUNTS_FILE); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); + + while ((ent = getmntent(fp)) != NULL) { + if (strncmp(ent->mnt_type, "bpf", 3) == 0) { + if (has_delegate_options(ent->mnt_opts)) + __show_token_info(ent); + } + } + + if (json_output) + jsonw_end_array(json_wtr); + + endmntent(fp); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + if (argc) + return BAD_ARG(); + + return show_token_info(); +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list }\n" + " %1$s %2$s help\n" + " " HELP_SPEC_OPTIONS " }\n" + "\n" + "", + bin_name, argv[-2]); + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_token(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c new file mode 100644 index 000000000..573a8d99f --- /dev/null +++ b/tools/bpf/bpftool/tracelog.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2015-2017 Daniel Borkmann */ +/* Copyright (c) 2018 Netronome Systems, Inc. */ + +#include <errno.h> +#include <limits.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <linux/magic.h> +#include <fcntl.h> +#include <sys/vfs.h> + +#include "main.h" + +#ifndef TRACEFS_MAGIC +# define TRACEFS_MAGIC 0x74726163 +#endif + +#define _textify(x) #x +#define textify(x) _textify(x) + +FILE *trace_pipe_fd; +char *buff; + +static int validate_tracefs_mnt(const char *mnt, unsigned long magic) +{ + struct statfs st_fs; + + if (statfs(mnt, &st_fs) < 0) + return -ENOENT; + if ((unsigned long)st_fs.f_type != magic) + return -ENOENT; + + return 0; +} + +static bool +find_tracefs_mnt_single(unsigned long magic, char *mnt, const char *mntpt) +{ + size_t src_len; + + if (validate_tracefs_mnt(mntpt, magic)) + return false; + + src_len = strlen(mntpt); + if (src_len + 1 >= PATH_MAX) { + p_err("tracefs mount point name too long"); + return false; + } + + strcpy(mnt, mntpt); + return true; +} + +static bool get_tracefs_pipe(char *mnt) +{ + static const char * const known_mnts[] = { + "/sys/kernel/tracing", + "/sys/kernel/debug/tracing", + }; + const char *pipe_name = "/trace_pipe"; + const char *fstype = "tracefs"; + char type[100], format[32]; + const char * const *ptr; + bool found = false; + FILE *fp; + + for (ptr = known_mnts; ptr < known_mnts + ARRAY_SIZE(known_mnts); ptr++) + if (find_tracefs_mnt_single(TRACEFS_MAGIC, mnt, *ptr)) + goto exit_found; + + fp = fopen("/proc/mounts", "r"); + if (!fp) + return false; + + /* Allow room for NULL terminating byte and pipe file name */ + snprintf(format, sizeof(format), "%%*s %%%zus %%99s %%*s %%*d %%*d\\n", + PATH_MAX - strlen(pipe_name) - 1); + while (fscanf(fp, format, mnt, type) == 2) + if (strcmp(type, fstype) == 0) { + found = true; + break; + } + fclose(fp); + + /* The string from fscanf() might be truncated, check mnt is valid */ + if (found && validate_tracefs_mnt(mnt, TRACEFS_MAGIC)) + goto exit_found; + + if (block_mount) + return false; + + p_info("could not find tracefs, attempting to mount it now"); + strcpy(mnt, known_mnts[0]); + if (mount_tracefs(mnt)) + return false; + +exit_found: + strcat(mnt, pipe_name); + return true; +} + +static void exit_tracelog(int signum) +{ + fclose(trace_pipe_fd); + free(buff); + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_destroy(&json_wtr); + } + + exit(0); +} + +int do_tracelog(int argc, char **argv) +{ + const struct sigaction act = { + .sa_handler = exit_tracelog + }; + char trace_pipe[PATH_MAX]; + size_t buff_len = 0; + + if (json_output) + jsonw_start_array(json_wtr); + + if (!get_tracefs_pipe(trace_pipe)) + return -1; + + trace_pipe_fd = fopen(trace_pipe, "r"); + if (!trace_pipe_fd) { + p_err("could not open trace pipe: %s", strerror(errno)); + return -1; + } + + sigaction(SIGHUP, &act, NULL); + sigaction(SIGINT, &act, NULL); + sigaction(SIGTERM, &act, NULL); + while (1) { + ssize_t ret; + + ret = getline(&buff, &buff_len, trace_pipe_fd); + if (ret <= 0) { + p_err("failed to read content from trace pipe: %s", + strerror(errno)); + break; + } + if (json_output) + jsonw_string(json_wtr, buff); + else + printf("%s", buff); + } + + fclose(trace_pipe_fd); + free(buff); + return -1; +} diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c new file mode 100644 index 000000000..5e7cb8b36 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -0,0 +1,434 @@ +// 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" +#include "main.h" +#include "xlated_dumper.h" + +static int kernel_syms_cmp(const void *sym_a, const void *sym_b) +{ + return ((struct kernel_sym *)sym_a)->address - + ((struct kernel_sym *)sym_b)->address; +} + +void kernel_syms_load(struct dump_data *dd) +{ + struct kernel_sym *sym; + char buff[256]; + void *tmp, *address; + FILE *fp; + + fp = fopen("/proc/kallsyms", "r"); + if (!fp) + return; + + while (fgets(buff, sizeof(buff), fp)) { + tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); + if (!tmp) { +out: + free(dd->sym_mapping); + dd->sym_mapping = NULL; + fclose(fp); + return; + } + dd->sym_mapping = tmp; + sym = &dd->sym_mapping[dd->sym_count]; + + /* 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")) { + dd->address_call_base = sym->address; + /* sysctl kernel.kptr_restrict was set */ + if (!sym->address) + goto out; + } + if (sym->address) + dd->sym_count++; + } + + fclose(fp); + + qsort(dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp); +} + +void kernel_syms_destroy(struct dump_data *dd) +{ + free(dd->sym_mapping); +} + +struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) +{ + struct kernel_sym sym = { + .address = key, + }; + + return dd->sym_mapping ? + bsearch(&sym, dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL; +} + +static void __printf(2, 3) print_insn(void *private_data, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vprintf(fmt, args); + va_end(args); +} + +static void __printf(2, 3) +print_insn_for_graph(void *private_data, const char *fmt, ...) +{ + char buf[64], *p; + va_list args; + + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + p = buf; + while (*p != '\0') { + if (*p == '\n') { + memmove(p + 3, p, strlen(buf) + 1 - (p - buf)); + /* Align each instruction dump row left. */ + *p++ = '\\'; + *p++ = 'l'; + /* Output multiline concatenation. */ + *p++ = '\\'; + } else if (*p == '<' || *p == '>' || *p == '|' || *p == '&') { + memmove(p + 1, p, strlen(buf) + 1 - (p - buf)); + /* Escape special character. */ + *p++ = '\\'; + } + + p++; + } + + printf("%s", buf); +} + +static void __printf(2, 3) +print_insn_json(void *private_data, const char *fmt, ...) +{ + unsigned int l = strlen(fmt); + char chomped_fmt[l]; + va_list args; + + va_start(args, fmt); + if (l > 0) { + strncpy(chomped_fmt, fmt, l - 1); + chomped_fmt[l - 1] = '\0'; + } + jsonw_vprintf_enquote(json_wtr, chomped_fmt, args); + va_end(args); +} + +static const char *print_call_pcrel(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address, + const struct bpf_insn *insn) +{ + if (!dd->nr_jited_ksyms) + /* Do not show address for interpreted programs */ + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d", insn->off); + else if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#%s", insn->off, sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#0x%lx", insn->off, address); + return dd->scratch_buff; +} + +static const char *print_call_helper(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address) +{ + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%s", sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%lx", address); + return dd->scratch_buff; +} + +static const char *print_call(void *private_data, + const struct bpf_insn *insn) +{ + struct dump_data *dd = private_data; + unsigned long address = dd->address_call_base + insn->imm; + struct kernel_sym *sym; + + if (insn->src_reg == BPF_PSEUDO_CALL && + (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms) + address = dd->jited_ksyms[insn->imm]; + + sym = kernel_syms_search(dd, address); + if (insn->src_reg == BPF_PSEUDO_CALL) + return print_call_pcrel(dd, sym, address, insn); + else + return print_call_helper(dd, sym, address); +} + +static const char *print_imm(void *private_data, + const struct bpf_insn *insn, + __u64 full_imm) +{ + struct dump_data *dd = private_data; + + if (insn->src_reg == BPF_PSEUDO_MAP_FD) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%d]", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%d][0]+%d", 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:%d]+%d", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_FUNC) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "subprog[%+d]", insn->imm); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%llx", (unsigned long long)full_imm); + return dd->scratch_buff; +} + +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) +{ + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_json, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_func_info *record; + struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; + bool double_insn = false; + unsigned int nr_skip = 0; + char func_sig[1024]; + unsigned int i; + + jsonw_start_array(json_wtr); + record = dd->func_info; + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + jsonw_start_object(json_wtr); + + if (btf && record) { + if (record->insn_off == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip); + if (linfo) { + btf_dump_linfo_json(btf, linfo, linum); + nr_skip++; + } + } + + jsonw_name(json_wtr, "disasm"); + print_bpf_insn(&cbs, insn + i, true); + + if (opcodes) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_object(json_wtr); + + jsonw_name(json_wtr, "code"); + jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code); + + jsonw_name(json_wtr, "src_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg); + + jsonw_name(json_wtr, "dst_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg); + + jsonw_name(json_wtr, "off"); + print_hex_data_json((uint8_t *)(&insn[i].off), 2); + + jsonw_name(json_wtr, "imm"); + if (double_insn && i < len - 1) + print_hex_data_json((uint8_t *)(&insn[i].imm), + 12); + else + print_hex_data_json((uint8_t *)(&insn[i].imm), + 4); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) +{ + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_func_info *record; + struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; + unsigned int nr_skip = 0; + bool double_insn = false; + char func_sig[1024]; + unsigned int i; + + record = dd->func_info; + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + + if (btf && record) { + if (record->insn_off == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') + printf("%s:\n", func_sig); + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip); + if (linfo) { + btf_dump_linfo_plain(btf, linfo, "; ", + linum); + nr_skip++; + } + } + + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + printf("%4u: ", i); + print_bpf_insn(&cbs, insn + i, true); + + if (opcodes) { + printf(" "); + fprint_hex(stdout, insn + i, 8, " "); + if (double_insn && i < len - 1) { + printf(" "); + fprint_hex(stdout, insn + i + 1, 8, " "); + } + printf("\n"); + } + } +} + +void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, + unsigned int start_idx, + bool opcodes, bool linum) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_for_graph, + .cb_call = print_call, + .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++) { + 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("%u: ", 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("| "); + } +} diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h new file mode 100644 index 000000000..db3ba0671 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_XLATED_DUMPER_H +#define __BPF_TOOL_XLATED_DUMPER_H + +#define SYM_MAX_NAME 256 +#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 { + unsigned long address_call_base; + struct kernel_sym *sym_mapping; + __u32 sym_count; + __u64 *jited_ksyms; + __u32 nr_jited_ksyms; + struct btf *btf; + void *func_info; + __u32 finfo_rec_size; + const struct bpf_prog_linfo *prog_linfo; + char scratch_buff[SYM_MAX_NAME + 8]; +}; + +void kernel_syms_load(struct dump_data *dd); +void kernel_syms_destroy(struct dump_data *dd); +struct kernel_sym *kernel_syms_search(struct dump_data *dd, unsigned long key); +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); +void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end, + unsigned int start_index, + bool opcodes, bool linum); + +#endif diff --git a/tools/bpf/resolve_btfids/.gitignore b/tools/bpf/resolve_btfids/.gitignore new file mode 100644 index 000000000..52d5e9721 --- /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 000000000..077de3829 --- /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 000000000..7672208f6 --- /dev/null +++ b/tools/bpf/resolve_btfids/Makefile @@ -0,0 +1,119 @@ +# SPDX-License-Identifier: GPL-2.0-only +include ../../scripts/Makefile.include +include ../../scripts/Makefile.arch + +srctree := $(abspath $(CURDIR)/../../../) + +ifeq ($(V),1) + msg = +else + 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="$(HOSTARCH)" \ + CROSS_COMPILE="" CLANG_CROSS_FLAGS="" EXTRA_CFLAGS="$(HOSTCFLAGS)" + +RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar +HOSTPKG_CONFIG ?= pkg-config +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 $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) + +ifneq ($(filter -static,$(EXTRA_LDFLAGS)),) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs --static 2>/dev/null || echo -lelf -lzstd) +else +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) +endif + +ZLIB_LIBS := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz) + +HOSTCFLAGS_resolve_btfids += -g \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(LIBBPF_INCLUDE) \ + -I$(SUBCMD_INCLUDE) \ + $(LIBELF_FLAGS) \ + -Wall -Werror + +LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) + +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) $(EXTRA_LDFLAGS) -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 000000000..f8a91fa75 --- /dev/null +++ b/tools/bpf/resolve_btfids/main.c @@ -0,0 +1,1583 @@ +// 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/kallsyms.h> +#include <linux/rbtree.h> +#include <linux/zalloc.h> +#include <linux/err.h> +#include <linux/limits.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 + +enum btf_id_kind { + BTF_ID_KIND_NONE, + BTF_ID_KIND_SYM, + BTF_ID_KIND_SET, + BTF_ID_KIND_SET8 +}; + +struct btf_id { + struct rb_node rb_node; + char *name; + union { + int id; + int cnt; + }; + enum btf_id_kind kind; + int addr_cnt; + Elf64_Addr addr[ADDR_CNT]; +}; + +struct object { + const char *path; + const char *btf_path; + const char *base_btf_path; + + struct btf *btf; + struct btf *base_btf; + bool distill_base; + + 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; +}; + +#define KF_IMPLICIT_ARGS (1 << 16) +#define KF_IMPL_SUFFIX "_impl" + +struct kfunc { + const char *name; + u32 btf_id; + u32 flags; +}; + +struct btf2btf_context { + struct btf *btf; + u32 *decl_tags; + u32 nr_decl_tags; + u32 max_decl_tags; + struct kfunc *kfuncs; + u32 nr_kfuncs; + u32 max_kfuncs; +}; + +static int verbose; +static int warnings; + +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, + const char *name, + enum btf_id_kind kind, + 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 = strdup(name); + if (!id->name) { + free(id); + return NULL; + } + id->kind = kind; + rb_link_node(&id->rb_node, parent, p); + rb_insert_color(&id->rb_node, root); + } + return id; +} + +static inline struct btf_id *btf_id__add(struct rb_root *root, + const char *name, + enum btf_id_kind kind) +{ + return __btf_id__add(root, name, kind, false); +} + +static inline struct btf_id *btf_id__add_unique(struct rb_root *root, + const char *name, + enum btf_id_kind kind) +{ + return __btf_id__add(root, name, kind, true); +} + +static int get_id(const char *prefix_end, char *buf, size_t buf_sz) +{ + /* + * __BTF_ID__func__vfs_truncate__0 + * prefix_end = ^ + * pos = ^ + */ + int len = strlen(prefix_end); + int pos = sizeof("__") - 1; + char *p; + + if (pos >= len) + return -1; + + if (len - pos >= buf_sz) + return -1; + + strcpy(buf, prefix_end + pos); + /* + * __BTF_ID__func__vfs_truncate__0 + * buf = ^ + * + * cut the unique id part + */ + p = strrchr(buf, '_'); + p--; + if (*p != '_') + return -1; + *p = '\0'; + + return 0; +} + +static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind kind) +{ + int len = strlen(name); + int prefixlen; + char *id; + + /* + * __BTF_ID__set__name + * name = ^ + * id = ^ + */ + switch (kind) { + case BTF_ID_KIND_SET: + prefixlen = sizeof(BTF_SET "__") - 1; + break; + case BTF_ID_KIND_SET8: + prefixlen = sizeof(BTF_SET8 "__") - 1; + break; + default: + pr_err("Unexpected kind %d passed to %s() for symbol %s\n", kind, __func__, name); + return NULL; + } + + id = name + prefixlen; + if (id >= name + len) { + pr_err("FAILED to parse set name: %s\n", name); + return NULL; + } + + return btf_id__add_unique(&obj->sets, id, kind); +} + +static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) +{ + char id[KSYM_NAME_LEN]; + + if (get_id(name + size, id, sizeof(id))) { + pr_err("FAILED to parse symbol name: %s\n", name); + return NULL; + } + + return btf_id__add(root, id, BTF_ID_KIND_SYM); +} + +static void btf_id__free_all(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); + next = rb_next(&id->rb_node); + rb_erase(&id->rb_node, root); + free(id->name); + free(id); + } +} + +static void bswap_32_data(void *data, u32 nr_bytes) +{ + u32 cnt, i; + u32 *ptr; + + cnt = nr_bytes / sizeof(u32); + ptr = data; + + for (i = 0; i < cnt; i++) + ptr[i] = bswap_32(ptr[i]); +} + +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_READ_MMAP_PRIVATE, 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)) { + /* + * If target endianness differs from host, we need to bswap32 + * the .BTF_ids section data on load, because .BTF_ids has + * Elf_Type = ELF_T_BYTE, and so libelf returns data buffer in + * the target endianness. We repeat this on dump. + */ + if (obj->efile.encoding != ELFDATANATIVE) { + pr_debug("bswap_32 .BTF_ids data from target to host endianness\n"); + bswap_32_data(data->d_buf, data->d_size); + } + obj->efile.idlist = data; + obj->efile.idlist_shndx = idx; + obj->efile.idlist_addr = sh.sh_addr; + } + } + + 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, BTF_ID_KIND_SET8); + /* + * 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; + /* set */ + } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { + id = add_set(obj, prefix, BTF_ID_KIND_SET); + /* + * 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; + } else { + pr_err("FAILED unsupported prefix %s\n", prefix); + return -1; + } + + if (!id) + return -EINVAL; + + 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 load_btf(struct object *obj) +{ + struct btf *base_btf = NULL, *btf = NULL; + int err; + + 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)); + goto out_err; + } + } + + btf = btf__parse_split(obj->btf_path ?: obj->path, base_btf); + err = libbpf_get_error(btf); + if (err) { + pr_err("FAILED: load BTF from %s: %s\n", + obj->btf_path ?: obj->path, strerror(-err)); + goto out_err; + } + + obj->base_btf = base_btf; + obj->btf = btf; + + return 0; + +out_err: + btf__free(base_btf); + btf__free(btf); + obj->base_btf = NULL; + obj->btf = NULL; + return err; +} + +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 *btf = obj->btf; + int err, type_id; + __u32 nr_types; + + 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); + warnings++; + } else { + id->id = type_id; + (*nr)--; + } + } + } + + err = 0; +out: + 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->kind != BTF_ID_KIND_SET && id->kind != BTF_ID_KIND_SET8) { + pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); + warnings++; + } + + 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; + int cnt; + + next = rb_first(&obj->sets); + while (next) { + struct btf_id_set8 *set8 = NULL; + struct btf_id_set *set = NULL; + 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; + } + + switch (id->kind) { + case BTF_ID_KIND_SET: + set = data->d_buf + off; + cnt = set->cnt; + qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id); + break; + case BTF_ID_KIND_SET8: + set8 = data->d_buf + off; + cnt = set8->cnt; + /* + * Make sure id is at the beginning of the pairs + * struct, otherwise the below qsort would not work. + */ + BUILD_BUG_ON((u32 *)set8->pairs != &set8->pairs[0].id); + qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id); + break; + default: + pr_err("Unexpected btf_id_kind %d for set '%s'\n", id->kind, id->name); + return -1; + } + + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", off, cnt, id->name); + + next = rb_next(next); + } + return 0; +} + +static int symbols_patch(struct object *obj) +{ + 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; + + return 0; +} + +static int dump_raw_data(const char *out_path, const void *data, u32 size) +{ + size_t written; + FILE *file; + + file = fopen(out_path, "wb"); + if (!file) { + pr_err("Couldn't open %s for writing\n", out_path); + return -1; + } + + written = fwrite(data, 1, size, file); + if (written != size) { + pr_err("Failed to write data to %s\n", out_path); + fclose(file); + unlink(out_path); + return -1; + } + + fclose(file); + pr_debug("Dumped %lu bytes of data to %s\n", size, out_path); + + return 0; +} + +static int dump_raw_btf_ids(struct object *obj, const char *out_path) +{ + Elf_Data *data = obj->efile.idlist; + int err; + + if (!data || !data->d_buf) { + pr_debug("%s has no BTF_ids data to dump\n", obj->path); + return 0; + } + + /* + * If target endianness differs from host, we need to bswap32 the + * .BTF_ids section data before dumping so that the output is in + * target endianness. + */ + if (obj->efile.encoding != ELFDATANATIVE) { + pr_debug("bswap_32 .BTF_ids data from host to target endianness\n"); + bswap_32_data(data->d_buf, data->d_size); + } + + err = dump_raw_data(out_path, data->d_buf, data->d_size); + if (err) + return -1; + + return 0; +} + +static int dump_raw_btf(struct btf *btf, const char *out_path) +{ + const void *raw_btf_data; + u32 raw_btf_size; + int err; + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!raw_btf_data) { + pr_err("btf__raw_data() failed\n"); + return -1; + } + + err = dump_raw_data(out_path, raw_btf_data, raw_btf_size); + if (err) + return -1; + + return 0; +} + +static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf, s32 type_id) +{ + const struct btf_type *t = btf__type_by_id(btf, type_id); + + while (btf_is_mod(t)) + t = btf__type_by_id(btf, t->type); + + return t; +} + +static int push_decl_tag_id(struct btf2btf_context *ctx, u32 decl_tag_id) +{ + u32 *arr = ctx->decl_tags; + u32 cap = ctx->max_decl_tags; + + if (ctx->nr_decl_tags + 1 > cap) { + cap = max(cap + 256, cap * 2); + arr = realloc(arr, sizeof(u32) * cap); + if (!arr) + return -ENOMEM; + ctx->max_decl_tags = cap; + ctx->decl_tags = arr; + } + + ctx->decl_tags[ctx->nr_decl_tags++] = decl_tag_id; + + return 0; +} + +static int push_kfunc(struct btf2btf_context *ctx, struct kfunc *kfunc) +{ + struct kfunc *arr = ctx->kfuncs; + u32 cap = ctx->max_kfuncs; + + if (ctx->nr_kfuncs + 1 > cap) { + cap = max(cap + 256, cap * 2); + arr = realloc(arr, sizeof(struct kfunc) * cap); + if (!arr) + return -ENOMEM; + ctx->max_kfuncs = cap; + ctx->kfuncs = arr; + } + + ctx->kfuncs[ctx->nr_kfuncs++] = *kfunc; + + return 0; +} + +static int collect_decl_tags(struct btf2btf_context *ctx) +{ + const u32 type_cnt = btf__type_cnt(ctx->btf); + struct btf *btf = ctx->btf; + const struct btf_type *t; + int err; + + for (u32 id = 1; id < type_cnt; id++) { + t = btf__type_by_id(btf, id); + if (!btf_is_decl_tag(t)) + continue; + err = push_decl_tag_id(ctx, id); + if (err) + return err; + } + + return 0; +} + +/* + * To find the kfunc flags having its struct btf_id (with ELF addresses) + * we need to find the address that is in range of a set8. + * If a set8 is found, then the flags are located at addr + 4 bytes. + * Return 0 (no flags!) if not found. + */ +static u32 find_kfunc_flags(struct object *obj, struct btf_id *kfunc_id) +{ + const u32 *elf_data_ptr = obj->efile.idlist->d_buf; + u64 set_lower_addr, set_upper_addr, addr; + struct btf_id *set_id; + struct rb_node *next; + u32 flags; + u64 idx; + + for (next = rb_first(&obj->sets); next; next = rb_next(next)) { + set_id = rb_entry(next, struct btf_id, rb_node); + if (set_id->kind != BTF_ID_KIND_SET8 || set_id->addr_cnt != 1) + continue; + + set_lower_addr = set_id->addr[0]; + set_upper_addr = set_lower_addr + set_id->cnt * sizeof(u64); + + for (u32 i = 0; i < kfunc_id->addr_cnt; i++) { + addr = kfunc_id->addr[i]; + /* + * Lower bound is exclusive to skip the 8-byte header of the set. + * Upper bound is inclusive to capture the last entry at offset 8*cnt. + */ + if (set_lower_addr < addr && addr <= set_upper_addr) { + pr_debug("found kfunc %s in BTF_ID_FLAGS %s\n", + kfunc_id->name, set_id->name); + idx = addr - obj->efile.idlist_addr; + idx = idx / sizeof(u32) + 1; + flags = elf_data_ptr[idx]; + + return flags; + } + } + } + + return 0; +} + +static int collect_kfuncs(struct object *obj, struct btf2btf_context *ctx) +{ + const char *tag_name, *func_name; + struct btf *btf = ctx->btf; + const struct btf_type *t; + u32 flags, func_id; + struct kfunc kfunc; + struct btf_id *id; + int err; + + if (ctx->nr_decl_tags == 0) + return 0; + + for (u32 i = 0; i < ctx->nr_decl_tags; i++) { + t = btf__type_by_id(btf, ctx->decl_tags[i]); + if (btf_kflag(t) || btf_decl_tag(t)->component_idx != -1) + continue; + + tag_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(tag_name, "bpf_kfunc") != 0) + continue; + + func_id = t->type; + t = btf__type_by_id(btf, func_id); + if (!btf_is_func(t)) + continue; + + func_name = btf__name_by_offset(btf, t->name_off); + if (!func_name) + continue; + + id = btf_id__find(&obj->funcs, func_name); + if (!id || id->kind != BTF_ID_KIND_SYM) + continue; + + flags = find_kfunc_flags(obj, id); + + kfunc.name = id->name; + kfunc.btf_id = func_id; + kfunc.flags = flags; + + err = push_kfunc(ctx, &kfunc); + if (err) + return err; + } + + return 0; +} + +static int build_btf2btf_context(struct object *obj, struct btf2btf_context *ctx) +{ + int err; + + ctx->btf = obj->btf; + + err = collect_decl_tags(ctx); + if (err) { + pr_err("ERROR: resolve_btfids: failed to collect decl tags from BTF\n"); + return err; + } + + err = collect_kfuncs(obj, ctx); + if (err) { + pr_err("ERROR: resolve_btfids: failed to collect kfuncs from BTF\n"); + return err; + } + + return 0; +} + + +/* Implicit BPF kfunc arguments can only be of particular types */ +static bool is_kf_implicit_arg(const struct btf *btf, const struct btf_param *p) +{ + static const char *const kf_implicit_arg_types[] = { + "bpf_prog_aux", + "btf_struct_meta", + }; + const struct btf_type *t; + const char *name; + + t = btf_type_skip_qualifiers(btf, p->type); + if (!btf_is_ptr(t)) + return false; + + t = btf_type_skip_qualifiers(btf, t->type); + if (!btf_is_struct(t)) + return false; + + name = btf__name_by_offset(btf, t->name_off); + if (!name) + return false; + + for (int i = 0; i < ARRAY_SIZE(kf_implicit_arg_types); i++) + if (strcmp(name, kf_implicit_arg_types[i]) == 0) + return true; + + return false; +} + +/* + * For a kfunc with KF_IMPLICIT_ARGS we do the following: + * 1. Add a new function with _impl suffix in the name, with the prototype + * of the original kfunc. + * 2. Add all decl tags except "bpf_kfunc" for the _impl func. + * 3. Add a new function prototype with modified list of arguments: + * omitting implicit args. + * 4. Change the prototype of the original kfunc to the new one. + * + * This way we transform the BTF associated with the kfunc from + * __bpf_kfunc bpf_foo(int arg1, void *implicit_arg); + * into + * bpf_foo_impl(int arg1, void *implicit_arg); + * __bpf_kfunc bpf_foo(int arg1); + * + * If a kfunc with KF_IMPLICIT_ARGS already has an _impl counterpart + * in BTF, then it's a legacy case: an _impl function is declared in the + * source code. In this case, we can skip adding an _impl function, but we + * still have to add a func prototype that omits implicit args. + */ +static int process_kfunc_with_implicit_args(struct btf2btf_context *ctx, struct kfunc *kfunc) +{ + s32 idx, new_proto_id, new_func_id, proto_id; + const char *param_name, *tag_name; + const struct btf_param *params; + enum btf_func_linkage linkage; + char tmp_name[KSYM_NAME_LEN]; + struct btf *btf = ctx->btf; + int err, len, nr_params; + struct btf_type *t; + + t = (struct btf_type *)btf__type_by_id(btf, kfunc->btf_id); + if (!t || !btf_is_func(t)) { + pr_err("ERROR: resolve_btfids: btf id %d is not a function\n", kfunc->btf_id); + return -EINVAL; + } + + linkage = btf_vlen(t); + + proto_id = t->type; + t = (struct btf_type *)btf__type_by_id(btf, proto_id); + if (!t || !btf_is_func_proto(t)) { + pr_err("ERROR: resolve_btfids: btf id %d is not a function prototype\n", proto_id); + return -EINVAL; + } + + len = snprintf(tmp_name, sizeof(tmp_name), "%s%s", kfunc->name, KF_IMPL_SUFFIX); + if (len < 0 || len >= sizeof(tmp_name)) { + pr_err("ERROR: function name is too long: %s%s\n", kfunc->name, KF_IMPL_SUFFIX); + return -E2BIG; + } + + if (btf__find_by_name_kind(btf, tmp_name, BTF_KIND_FUNC) > 0) { + pr_debug("resolve_btfids: function %s already exists in BTF\n", tmp_name); + goto add_new_proto; + } + + /* Add a new function with _impl suffix and original prototype */ + new_func_id = btf__add_func(btf, tmp_name, linkage, proto_id); + if (new_func_id < 0) { + pr_err("ERROR: resolve_btfids: failed to add func %s to BTF\n", tmp_name); + return new_func_id; + } + + /* Copy all decl tags except "bpf_kfunc" from the original kfunc to the new one */ + for (int i = 0; i < ctx->nr_decl_tags; i++) { + t = (struct btf_type *)btf__type_by_id(btf, ctx->decl_tags[i]); + if (t->type != kfunc->btf_id) + continue; + + tag_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(tag_name, "bpf_kfunc") == 0) + continue; + + idx = btf_decl_tag(t)->component_idx; + + if (btf_kflag(t)) + err = btf__add_decl_attr(btf, tag_name, new_func_id, idx); + else + err = btf__add_decl_tag(btf, tag_name, new_func_id, idx); + + if (err < 0) { + pr_err("ERROR: resolve_btfids: failed to add decl tag %s for %s\n", + tag_name, tmp_name); + return -EINVAL; + } + } + +add_new_proto: + t = (struct btf_type *)btf__type_by_id(btf, proto_id); + new_proto_id = btf__add_func_proto(btf, t->type); + if (new_proto_id < 0) { + pr_err("ERROR: resolve_btfids: failed to add func proto for %s\n", kfunc->name); + return new_proto_id; + } + + /* Add non-implicit args to the new prototype */ + t = (struct btf_type *)btf__type_by_id(btf, proto_id); + nr_params = btf_vlen(t); + for (int i = 0; i < nr_params; i++) { + params = btf_params(t); + if (is_kf_implicit_arg(btf, ¶ms[i])) + break; + param_name = btf__name_by_offset(btf, params[i].name_off); + err = btf__add_func_param(btf, param_name, params[i].type); + if (err < 0) { + pr_err("ERROR: resolve_btfids: failed to add param %s for %s\n", + param_name, kfunc->name); + return err; + } + t = (struct btf_type *)btf__type_by_id(btf, proto_id); + } + + /* Finally change the prototype of the original kfunc to the new one */ + t = (struct btf_type *)btf__type_by_id(btf, kfunc->btf_id); + t->type = new_proto_id; + + pr_debug("resolve_btfids: updated BTF for kfunc with implicit args %s\n", kfunc->name); + + return 0; +} + +static int btf2btf(struct object *obj) +{ + struct btf2btf_context ctx = {}; + int err; + + err = build_btf2btf_context(obj, &ctx); + if (err) + goto out; + + for (u32 i = 0; i < ctx.nr_kfuncs; i++) { + struct kfunc *kfunc = &ctx.kfuncs[i]; + + if (!(kfunc->flags & KF_IMPLICIT_ARGS)) + continue; + + err = process_kfunc_with_implicit_args(&ctx, kfunc); + if (err) + goto out; + } + + err = 0; +out: + free(ctx.decl_tags); + free(ctx.kfuncs); + + return err; +} + +/* + * Sort types by name in ascending order resulting in all + * anonymous types being placed before named types. + */ +static int cmp_type_names(const void *a, const void *b, void *priv) +{ + struct btf *btf = (struct btf *)priv; + const struct btf_type *ta = btf__type_by_id(btf, *(__u32 *)a); + const struct btf_type *tb = btf__type_by_id(btf, *(__u32 *)b); + const char *na, *nb; + int r; + + na = btf__str_by_offset(btf, ta->name_off); + nb = btf__str_by_offset(btf, tb->name_off); + r = strcmp(na, nb); + if (r != 0) + return r; + + /* preserve original relative order of anonymous or same-named types */ + return *(__u32 *)a < *(__u32 *)b ? -1 : 1; +} + +static int sort_btf_by_name(struct btf *btf) +{ + __u32 *permute_ids = NULL, *id_map = NULL; + int nr_types, i, err = 0; + __u32 start_id = 0, id; + + if (btf__base_btf(btf)) + start_id = btf__type_cnt(btf__base_btf(btf)); + nr_types = btf__type_cnt(btf) - start_id; + + permute_ids = calloc(nr_types, sizeof(*permute_ids)); + if (!permute_ids) { + err = -ENOMEM; + goto out; + } + + id_map = calloc(nr_types, sizeof(*id_map)); + if (!id_map) { + err = -ENOMEM; + goto out; + } + + for (i = 0, id = start_id; i < nr_types; i++, id++) + permute_ids[i] = id; + + qsort_r(permute_ids, nr_types, sizeof(*permute_ids), cmp_type_names, + btf); + + for (i = 0; i < nr_types; i++) { + id = permute_ids[i] - start_id; + id_map[id] = i + start_id; + } + + err = btf__permute(btf, id_map, nr_types, NULL); + if (err) + pr_err("FAILED: btf permute: %s\n", strerror(-err)); + +out: + free(permute_ids); + free(id_map); + return err; +} + +static int finalize_btf(struct object *obj) +{ + struct btf *base_btf = obj->base_btf, *btf = obj->btf; + int err; + + if (obj->base_btf && obj->distill_base) { + err = btf__distill_base(obj->btf, &base_btf, &btf); + if (err) { + pr_err("FAILED to distill base BTF: %s\n", strerror(errno)); + goto out_err; + } + + btf__free(obj->base_btf); + btf__free(obj->btf); + obj->base_btf = base_btf; + obj->btf = btf; + } + + err = sort_btf_by_name(obj->btf); + if (err) { + pr_err("FAILED to sort BTF: %s\n", strerror(errno)); + goto out_err; + } + + return 0; + +out_err: + btf__free(base_btf); + btf__free(btf); + obj->base_btf = NULL; + obj->btf = NULL; + + return err; +} + +static inline int make_out_path(char *buf, u32 buf_sz, const char *in_path, const char *suffix) +{ + int len = snprintf(buf, buf_sz, "%s%s", in_path, suffix); + + if (len < 0 || len >= buf_sz) { + pr_err("Output path is too long: %s%s\n", in_path, suffix); + return -E2BIG; + } + + return 0; +} + +/* + * Patch the .BTF_ids section of an ELF file with data from provided file. + * Equivalent to: objcopy --update-section .BTF_ids=<btfids> <elf> + * + * 1. Find .BTF_ids section in the ELF + * 2. Verify that blob file size matches section size + * 3. Update section data buffer with blob data + * 4. Write the ELF file + */ +static int patch_btfids(const char *btfids_path, const char *elf_path) +{ + Elf_Scn *scn = NULL; + FILE *btfids_file; + size_t shdrstrndx; + int fd, err = -1; + Elf_Data *data; + struct stat st; + GElf_Shdr sh; + char *name; + Elf *elf; + + elf_version(EV_CURRENT); + + fd = open(elf_path, O_RDWR, 0666); + if (fd < 0) { + pr_err("FAILED to open %s: %s\n", elf_path, strerror(errno)); + return -1; + } + + 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; + } + + elf_flagelf(elf, ELF_C_SET, ELF_F_LAYOUT); + + if (elf_getshdrstrndx(elf, &shdrstrndx) != 0) { + pr_err("FAILED cannot get shdr str ndx\n"); + goto out; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + + if (gelf_getshdr(scn, &sh) != &sh) { + pr_err("FAILED to get section header\n"); + goto out; + } + + name = elf_strptr(elf, shdrstrndx, sh.sh_name); + if (!name) + continue; + + if (strcmp(name, BTF_IDS_SECTION) == 0) + break; + } + + if (!scn) { + pr_err("FAILED: section %s not found in %s\n", BTF_IDS_SECTION, elf_path); + goto out; + } + + data = elf_getdata(scn, NULL); + if (!data) { + pr_err("FAILED to get %s section data from %s\n", BTF_IDS_SECTION, elf_path); + goto out; + } + + if (stat(btfids_path, &st) < 0) { + pr_err("FAILED to stat %s: %s\n", btfids_path, strerror(errno)); + goto out; + } + + if ((size_t)st.st_size != data->d_size) { + pr_err("FAILED: size mismatch - %s section in %s is %zu bytes, %s is %zu bytes\n", + BTF_IDS_SECTION, elf_path, data->d_size, btfids_path, (size_t)st.st_size); + goto out; + } + + btfids_file = fopen(btfids_path, "rb"); + if (!btfids_file) { + pr_err("FAILED to open %s: %s\n", btfids_path, strerror(errno)); + goto out; + } + + pr_debug("Copying data from %s to %s section of %s (%zu bytes)\n", + btfids_path, BTF_IDS_SECTION, elf_path, data->d_size); + + if (fread(data->d_buf, data->d_size, 1, btfids_file) != 1) { + pr_err("FAILED to read %s\n", btfids_path); + fclose(btfids_file); + goto out; + } + fclose(btfids_file); + + elf_flagdata(data, ELF_C_SET, ELF_F_DIRTY); + if (elf_update(elf, ELF_C_WRITE) < 0) { + pr_err("FAILED to update ELF file %s\n", elf_path); + goto out; + } + + err = 0; +out: + elf_end(elf); + close(fd); + + return err; +} + +static const char * const resolve_btfids_usage[] = { + "resolve_btfids [<options>] <ELF object>", + "resolve_btfids --patch_btfids <.BTF_ids file> <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, + }; + const char *btfids_path = NULL; + bool fatal_warnings = false; + bool resolve_btfids = true; + char out_path[PATH_MAX]; + + struct option btfid_options[] = { + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show errors, etc)"), + OPT_STRING(0, "btf", &obj.btf_path, "file", + "path to a file with input BTF data"), + OPT_STRING('b', "btf_base", &obj.base_btf_path, "file", + "path of file providing base BTF"), + OPT_BOOLEAN(0, "fatal_warnings", &fatal_warnings, + "turn warnings into errors"), + OPT_BOOLEAN(0, "distill_base", &obj.distill_base, + "distill --btf_base and emit .BTF.base section data"), + OPT_STRING(0, "patch_btfids", &btfids_path, "file", + "path to .BTF_ids section data blob to patch into ELF file"), + 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 (btfids_path) + return patch_btfids(btfids_path, obj.path); + + 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, skip symbols resolution\n"); + resolve_btfids = false; + } + + if (resolve_btfids) + if (symbols_collect(&obj)) + goto out; + + if (load_btf(&obj)) + goto out; + + if (btf2btf(&obj)) + goto out; + + if (finalize_btf(&obj)) + goto out; + + if (!resolve_btfids) + goto dump_btf; + + if (symbols_resolve(&obj)) + goto out; + + if (symbols_patch(&obj)) + goto out; + + err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_IDS_SECTION); + err = err ?: dump_raw_btf_ids(&obj, out_path); + if (err) + goto out; + +dump_btf: + err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_ELF_SEC); + err = err ?: dump_raw_btf(obj.btf, out_path); + if (err) + goto out; + + if (obj.base_btf && obj.distill_base) { + err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_BASE_ELF_SEC); + err = err ?: dump_raw_btf(obj.base_btf, out_path); + if (err) + goto out; + } + + if (!(fatal_warnings && warnings)) + err = 0; +out: + btf__free(obj.base_btf); + btf__free(obj.btf); + btf_id__free_all(&obj.structs); + btf_id__free_all(&obj.unions); + btf_id__free_all(&obj.typedefs); + btf_id__free_all(&obj.funcs); + btf_id__free_all(&obj.sets); + if (obj.efile.elf) { + elf_end(obj.efile.elf); + close(obj.efile.fd); + } + return err; +} |