| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20240206111150.zqjyx33wqipqitzu@M910t>
Date: Tue, 6 Feb 2024 19:11:50 +0800
From: Changbin Du <changbin.du@...wei.com>
To: Adrian Hunter <adrian.hunter@...el.com>
CC: Changbin Du <changbin.du@...wei.com>, Peter Zijlstra
<peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>, Arnaldo Carvalho de
Melo <acme@...nel.org>, Mark Rutland <mark.rutland@....com>, Alexander
Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>, Ian Rogers <irogers@...gle.com>,
<linux-kernel@...r.kernel.org>, <linux-perf-users@...r.kernel.org>, Andi
Kleen <ak@...ux.intel.com>, Thomas Richter <tmricht@...ux.ibm.com>,
<changbin.du@...il.com>
Subject: Re: [PATCH v6 2/5] perf: util: use capstone disasm engine to show
assembly instructions
On Tue, Feb 06, 2024 at 12:33:10PM +0200, Adrian Hunter wrote:
> On 6/02/24 04:14, Changbin Du wrote:
> > Currently, the instructions of samples are shown as raw hex strings
> > which are hard to read. x86 has a special option '--xed' to disassemble
> > the hex string via intel XED tool.
> >
> > Here we use capstone as our disassembler engine to give more friendly
> > instructions. We select libcapstone because capstone can provide more
> > insn details. Perf will fallback to raw instructions if libcapstone is
> > not available.
> >
> > The advantages compared to XED tool:
> > * Support arm, arm64, x86-32, x86_64 (more could be supported),
> > xed only for x86_64.
> > * Immediate address operands are shown as symbol+offs.
> >
> > Signed-off-by: Changbin Du <changbin.du@...wei.com>
> >
> > ---
> > v3:
> > - show warning msg if libcapstone is not available.
> > v2:
> > - line up the output by preceding two tabs. (Adrian Hunter)
> > - removed the tailing space. (Adrian Hunter)
> > - forward declaration for perf_sample, thread, machine. (Adrian Hunter)
> > - other trivial fixes (Adrian Hunter)
> > ---
> > tools/perf/builtin-script.c | 8 +--
> > tools/perf/util/Build | 1 +
> > tools/perf/util/print_insn.c | 134 +++++++++++++++++++++++++++++++++++
> > tools/perf/util/print_insn.h | 16 +++++
> > 4 files changed, 154 insertions(+), 5 deletions(-)
> > create mode 100644 tools/perf/util/print_insn.c
> > create mode 100644 tools/perf/util/print_insn.h
> >
> > diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> > index b1f57401ff23..4817a37f16e2 100644
> > --- a/tools/perf/builtin-script.c
> > +++ b/tools/perf/builtin-script.c
> > @@ -34,6 +34,7 @@
> > #include "util/event.h"
> > #include "ui/ui.h"
> > #include "print_binary.h"
> > +#include "print_insn.h"
> > #include "archinsn.h"
> > #include <linux/bitmap.h>
> > #include <linux/kernel.h>
> > @@ -1511,11 +1512,8 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
> > if (PRINT_FIELD(INSNLEN))
> > printed += fprintf(fp, " ilen: %d", sample->insn_len);
> > if (PRINT_FIELD(INSN) && sample->insn_len) {
> > - int i;
> > -
> > - printed += fprintf(fp, " insn:");
> > - for (i = 0; i < sample->insn_len; i++)
> > - printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
> > + printed += fprintf(fp, " insn: ");
> > + printed += sample__fprintf_insn_raw(sample, fp);
> > }
> > if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
> > printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
> > diff --git a/tools/perf/util/Build b/tools/perf/util/Build
> > index 8027f450fa3e..2cbeeb79b6ef 100644
> > --- a/tools/perf/util/Build
> > +++ b/tools/perf/util/Build
> > @@ -32,6 +32,7 @@ perf-y += perf_regs.o
> > perf-y += perf-regs-arch/
> > perf-y += path.o
> > perf-y += print_binary.o
> > +perf-y += print_insn.o
> > perf-y += rlimit.o
> > perf-y += argv_split.o
> > perf-y += rbtree.o
> > diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
> > new file mode 100644
> > index 000000000000..163307a02274
> > --- /dev/null
> > +++ b/tools/perf/util/print_insn.c
> > @@ -0,0 +1,134 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Instruction binary disassembler based on capstone.
> > + *
> > + * Author(s): Changbin Du <changbin.du@...wei.com>
> > + */
> > +#include <string.h>
> > +#include <stdbool.h>
> > +#include "debug.h"
> > +#include "event.h"
> > +#include "symbol.h"
> > +#include "machine.h"
> > +#include "thread.h"
> > +#include "print_insn.h"
> > +
> > +size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
> > +{
> > + int printed = 0;
> > +
> > + for (int i = 0; i < sample->insn_len; i++) {
> > + printed += fprintf(fp, "%02x ", (unsigned char)sample->insn[i]);
>
> Same as last time, there are 2 spaces between bytes
> instead of 1. It needs:
>
> "%02x " -> "%02x"
>
My fault. Fixed. Thanks!
> > + if (sample->insn_len - i > 1)
> > + printed += fprintf(fp, " ");
> > + }
> > + return printed;
> > +}
> > +
> > +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> > +#include <capstone/capstone.h>
> > +
> > +static int capstone_init(struct machine *machine, csh *cs_handle)
> > +{
> > + cs_arch arch;
> > + cs_mode mode;
> > +
> > + if (machine__is(machine, "x86_64")) {
> > + arch = CS_ARCH_X86;
> > + mode = CS_MODE_64;
> > + } else if (machine__normalized_is(machine, "x86")) {
> > + arch = CS_ARCH_X86;
> > + mode = CS_MODE_32;
> > + } else if (machine__normalized_is(machine, "arm64")) {
> > + arch = CS_ARCH_ARM64;
> > + mode = CS_MODE_ARM;
> > + } else if (machine__normalized_is(machine, "arm")) {
> > + arch = CS_ARCH_ARM;
> > + mode = CS_MODE_ARM + CS_MODE_V8;
> > + } else if (machine__normalized_is(machine, "s390")) {
> > + arch = CS_ARCH_SYSZ;
> > + mode = CS_MODE_BIG_ENDIAN;
> > + } else {
> > + return -1;
> > + }
> > +
> > + if (cs_open(arch, mode, cs_handle) != CS_ERR_OK) {
> > + pr_warning_once("cs_open failed\n");
> > + return -1;
> > + }
> > +
> > + if (machine__normalized_is(machine, "x86")) {
> > + cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
> > + /*
> > + * Resolving address operands to symbols is implemented
> > + * on x86 by investigating instruction details.
> > + */
> > + cs_option(*cs_handle, CS_OPT_DETAIL, CS_OPT_ON);
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
> > + cs_insn *insn, FILE *fp)
> > +{
> > + struct addr_location al;
> > + size_t printed = 0;
> > +
> > + if (insn->detail && insn->detail->x86.op_count == 1) {
> > + cs_x86_op *op = &insn->detail->x86.operands[0];
> > +
> > + addr_location__init(&al);
> > + if (op->type == X86_OP_IMM &&
> > + thread__find_symbol(thread, sample->cpumode, op->imm, &al)) {
> > + printed += fprintf(fp, "%s ", insn[0].mnemonic);
> > + printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
> > + addr_location__exit(&al);
> > + return printed;
> > + }
> > + addr_location__exit(&al);
> > + }
> > +
> > + printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
> > + return printed;
> > +}
> > +
> > +size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread,
> > + struct machine *machine, FILE *fp)
> > +{
> > + csh cs_handle;
> > + cs_insn *insn;
> > + size_t count;
> > + size_t printed = 0;
> > + int ret;
> > +
> > + /* TODO: Try to initiate capstone only once but need a proper place. */
> > + ret = capstone_init(machine, &cs_handle);
> > + if (ret < 0) {
> > + /* fallback */
> > + return sample__fprintf_insn_raw(sample, fp);
> > + }
> > +
> > + count = cs_disasm(cs_handle, (uint8_t *)sample->insn, sample->insn_len,
> > + sample->ip, 1, &insn);
> > + if (count > 0) {
> > + if (machine__normalized_is(machine, "x86"))
> > + printed += print_insn_x86(sample, thread, &insn[0], fp);
> > + else
> > + printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
> > + cs_free(insn, count);
> > + } else {
> > + printed += fprintf(fp, "illegal instruction");
> > + }
> > +
> > + cs_close(&cs_handle);
> > + return printed;
> > +}
> > +#else
> > +size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread __maybe_unused,
> > + struct machine *machine __maybe_unused, FILE *fp)
> > +{
> > + pr_warning_once("perf needs to be built with libcapstone support to disassemble instructions\n");
> > + return sample__fprintf_insn_raw(sample, fp);
>
> The validation stops this being called so could just leave
> out the 2 lines above, and add __maybe_unused as necessary.
>
I expect this being a generic api and could be invoked by other functions which
may not require the validation (raw code is acceptable).
> > +}
> > +#endif
> > diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
> > new file mode 100644
> > index 000000000000..80dda6da7c60
> > --- /dev/null
> > +++ b/tools/perf/util/print_insn.h
> > @@ -0,0 +1,16 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +#ifndef PERF_PRINT_INSN_H
> > +#define PERF_PRINT_INSN_H
> > +
> > +#include <stddef.h>
> > +#include <stdio.h>
> > +
> > +struct perf_sample;
> > +struct thread;
> > +struct machine;
> > +
> > +size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread,
> > + struct machine *machine, FILE *fp);
> > +size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
> > +
> > +#endif /* PERF_PRINT_INSN_H */
>
--
Cheers,
Changbin Du
Powered by blists - more mailing lists