You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
kernel_samsung_sm7125/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c

275 lines
6.6 KiB

/*
* intel_pt_insn_decoder.c: Intel Processor Trace support
* Copyright (c) 2013-2014, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
*/
#include <stdio.h>
#include <string.h>
#include <endian.h>
#include <byteswap.h>
#include "event.h"
#include "insn.h"
#include "inat.c"
#include "insn.c"
#include "intel-pt-insn-decoder.h"
perf script: Add 'brstackinsn' for branch stacks Implement printing instruction sequences as hex dump for branch stacks. This relies on the x86 instruction decoder used by the PT decoder to find the lengths of instructions to dump them individually. This is good enough for pattern matching. This allows to study hot paths for individual samples, together with branch misprediction and cycle count / IPC information if available (on Skylake systems). % perf record -b ... % perf script -F brstackinsn ... read_hpet+67: ffffffff9905b843 insn: 74 ea # PRED ffffffff9905b82f insn: 85 c9 ffffffff9905b831 insn: 74 12 ffffffff9905b833 insn: f3 90 ffffffff9905b835 insn: 48 8b 0f ffffffff9905b838 insn: 48 89 ca ffffffff9905b83b insn: 48 c1 ea 20 ffffffff9905b83f insn: 39 f2 ffffffff9905b841 insn: 89 d0 ffffffff9905b843 insn: 74 ea # PRED Only works when no special branch filters are specified. Occasionally the path does not reach up to the sample IP, as the LBRs may be frozen before executing a final jump. In this case we print a special message. The instruction dumper piggy backs on the existing infrastructure from the IP PT decoder. An earlier iteration of this patch relied on a disassembler, but this version only uses the existing instruction decoder. Committer note: Added hint about how to get suitable perf.data files for use with '-F brstackinsm': $ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (8 samples) ] $ $ perf script -F brstackinsn Display of branch stack assembler requested, but non all-branch filter set Hint: run 'perf record -b ...' $ Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Link: http://lkml.kernel.org/r/20170223234634.583-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
8 years ago
#include "dump-insn.h"
#if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
#error Instruction buffer size too small
#endif
/* Based on branch_type() from arch/x86/events/intel/lbr.c */
static void intel_pt_insn_decoder(struct insn *insn,
struct intel_pt_insn *intel_pt_insn)
{
enum intel_pt_insn_op op = INTEL_PT_OP_OTHER;
enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
int ext;
intel_pt_insn->rel = 0;
if (insn_is_avx(insn)) {
intel_pt_insn->op = INTEL_PT_OP_OTHER;
intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
intel_pt_insn->length = insn->length;
return;
}
switch (insn->opcode.bytes[0]) {
case 0xf:
switch (insn->opcode.bytes[1]) {
case 0x05: /* syscall */
case 0x34: /* sysenter */
op = INTEL_PT_OP_SYSCALL;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0x07: /* sysret */
case 0x35: /* sysexit */
op = INTEL_PT_OP_SYSRET;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0x80 ... 0x8f: /* jcc */
op = INTEL_PT_OP_JCC;
branch = INTEL_PT_BR_CONDITIONAL;
break;
default:
break;
}
break;
case 0x70 ... 0x7f: /* jcc */
op = INTEL_PT_OP_JCC;
branch = INTEL_PT_BR_CONDITIONAL;
break;
case 0xc2: /* near ret */
case 0xc3: /* near ret */
case 0xca: /* far ret */
case 0xcb: /* far ret */
op = INTEL_PT_OP_RET;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0xcf: /* iret */
op = INTEL_PT_OP_IRET;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0xcc ... 0xce: /* int */
op = INTEL_PT_OP_INT;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0xe8: /* call near rel */
op = INTEL_PT_OP_CALL;
branch = INTEL_PT_BR_UNCONDITIONAL;
break;
case 0x9a: /* call far absolute */
op = INTEL_PT_OP_CALL;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0xe0 ... 0xe2: /* loop */
op = INTEL_PT_OP_LOOP;
branch = INTEL_PT_BR_CONDITIONAL;
break;
case 0xe3: /* jcc */
op = INTEL_PT_OP_JCC;
branch = INTEL_PT_BR_CONDITIONAL;
break;
case 0xe9: /* jmp */
case 0xeb: /* jmp */
op = INTEL_PT_OP_JMP;
branch = INTEL_PT_BR_UNCONDITIONAL;
break;
case 0xea: /* far jmp */
op = INTEL_PT_OP_JMP;
branch = INTEL_PT_BR_INDIRECT;
break;
case 0xff: /* call near absolute, call far absolute ind */
ext = (insn->modrm.bytes[0] >> 3) & 0x7;
switch (ext) {
case 2: /* near ind call */
case 3: /* far ind call */
op = INTEL_PT_OP_CALL;
branch = INTEL_PT_BR_INDIRECT;
break;
case 4:
case 5:
op = INTEL_PT_OP_JMP;
branch = INTEL_PT_BR_INDIRECT;
break;
default:
break;
}
break;
default:
break;
}
intel_pt_insn->op = op;
intel_pt_insn->branch = branch;
intel_pt_insn->length = insn->length;
if (branch == INTEL_PT_BR_CONDITIONAL ||
branch == INTEL_PT_BR_UNCONDITIONAL) {
#if __BYTE_ORDER == __BIG_ENDIAN
switch (insn->immediate.nbytes) {
case 1:
intel_pt_insn->rel = insn->immediate.value;
break;
case 2:
intel_pt_insn->rel =
bswap_16((short)insn->immediate.value);
break;
case 4:
intel_pt_insn->rel = bswap_32(insn->immediate.value);
break;
perf tools: Fix build on powerpc broken by pt/bts It is theoretically possible to process perf.data files created on x86 and that contain Intel PT or Intel BTS data, on any other architecture, which is why it is possible for there to be build errors on powerpc caused by pt/bts. The errors were: util/intel-pt-decoder/intel-pt-insn-decoder.c: In function ‘intel_pt_insn_decoder’: util/intel-pt-decoder/intel-pt-insn-decoder.c:138:3: error: switch missing default case [-Werror=switch-default] switch (insn->immediate.nbytes) { ^ cc1: all warnings being treated as errors linux-acme.git/tools/perf/perf-obj/libperf.a(libperf-in.o): In function `intel_pt_synth_branch_sample': sources/linux-acme.git/tools/perf/util/intel-pt.c:871: undefined reference to `tsc_to_perf_time' linux-acme.git/tools/perf/perf-obj/libperf.a(libperf-in.o): In function `intel_pt_sample': sources/linux-acme.git/tools/perf/util/intel-pt.c:915: undefined reference to `tsc_to_perf_time' sources/linux-acme.git/tools/perf/util/intel-pt.c:962: undefined reference to `tsc_to_perf_time' linux-acme.git/tools/perf/perf-obj/libperf.a(libperf-in.o): In function `intel_pt_process_event': sources/linux-acme.git/tools/perf/util/intel-pt.c:1454: undefined reference to `perf_time_to_tsc' Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1441046384-28663-1-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
9 years ago
default:
intel_pt_insn->rel = 0;
break;
}
#else
intel_pt_insn->rel = insn->immediate.value;
#endif
}
}
int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
struct intel_pt_insn *intel_pt_insn)
{
struct insn insn;
insn_init(&insn, buf, len, x86_64);
insn_get_length(&insn);
if (!insn_complete(&insn) || insn.length > len)
return -1;
intel_pt_insn_decoder(&insn, intel_pt_insn);
if (insn.length < INTEL_PT_INSN_BUF_SZ)
memcpy(intel_pt_insn->buf, buf, insn.length);
else
memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_BUF_SZ);
return 0;
}
perf script: Add 'brstackinsn' for branch stacks Implement printing instruction sequences as hex dump for branch stacks. This relies on the x86 instruction decoder used by the PT decoder to find the lengths of instructions to dump them individually. This is good enough for pattern matching. This allows to study hot paths for individual samples, together with branch misprediction and cycle count / IPC information if available (on Skylake systems). % perf record -b ... % perf script -F brstackinsn ... read_hpet+67: ffffffff9905b843 insn: 74 ea # PRED ffffffff9905b82f insn: 85 c9 ffffffff9905b831 insn: 74 12 ffffffff9905b833 insn: f3 90 ffffffff9905b835 insn: 48 8b 0f ffffffff9905b838 insn: 48 89 ca ffffffff9905b83b insn: 48 c1 ea 20 ffffffff9905b83f insn: 39 f2 ffffffff9905b841 insn: 89 d0 ffffffff9905b843 insn: 74 ea # PRED Only works when no special branch filters are specified. Occasionally the path does not reach up to the sample IP, as the LBRs may be frozen before executing a final jump. In this case we print a special message. The instruction dumper piggy backs on the existing infrastructure from the IP PT decoder. An earlier iteration of this patch relied on a disassembler, but this version only uses the existing instruction decoder. Committer note: Added hint about how to get suitable perf.data files for use with '-F brstackinsm': $ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (8 samples) ] $ $ perf script -F brstackinsn Display of branch stack assembler requested, but non all-branch filter set Hint: run 'perf record -b ...' $ Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Link: http://lkml.kernel.org/r/20170223234634.583-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
8 years ago
const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
u8 *inbuf, int inlen, int *lenp)
{
struct insn insn;
int n, i;
int left;
insn_init(&insn, inbuf, inlen, x->is64bit);
insn_get_length(&insn);
if (!insn_complete(&insn) || insn.length > inlen)
return "<bad>";
if (lenp)
*lenp = insn.length;
left = sizeof(x->out);
n = snprintf(x->out, left, "insn: ");
left -= n;
for (i = 0; i < insn.length; i++) {
n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
left -= n;
}
return x->out;
}
const char *branch_name[] = {
[INTEL_PT_OP_OTHER] = "Other",
[INTEL_PT_OP_CALL] = "Call",
[INTEL_PT_OP_RET] = "Ret",
[INTEL_PT_OP_JCC] = "Jcc",
[INTEL_PT_OP_JMP] = "Jmp",
[INTEL_PT_OP_LOOP] = "Loop",
[INTEL_PT_OP_IRET] = "IRet",
[INTEL_PT_OP_INT] = "Int",
[INTEL_PT_OP_SYSCALL] = "Syscall",
[INTEL_PT_OP_SYSRET] = "Sysret",
};
const char *intel_pt_insn_name(enum intel_pt_insn_op op)
{
return branch_name[op];
}
int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
size_t buf_len)
{
switch (intel_pt_insn->branch) {
case INTEL_PT_BR_CONDITIONAL:
case INTEL_PT_BR_UNCONDITIONAL:
return snprintf(buf, buf_len, "%s %s%d",
intel_pt_insn_name(intel_pt_insn->op),
intel_pt_insn->rel > 0 ? "+" : "",
intel_pt_insn->rel);
case INTEL_PT_BR_NO_BRANCH:
case INTEL_PT_BR_INDIRECT:
return snprintf(buf, buf_len, "%s",
intel_pt_insn_name(intel_pt_insn->op));
default:
break;
}
return 0;
}
int intel_pt_insn_type(enum intel_pt_insn_op op)
{
switch (op) {
case INTEL_PT_OP_OTHER:
return 0;
case INTEL_PT_OP_CALL:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL;
case INTEL_PT_OP_RET:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN;
case INTEL_PT_OP_JCC:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
case INTEL_PT_OP_JMP:
return PERF_IP_FLAG_BRANCH;
case INTEL_PT_OP_LOOP:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
case INTEL_PT_OP_IRET:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_INTERRUPT;
case INTEL_PT_OP_INT:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
PERF_IP_FLAG_INTERRUPT;
case INTEL_PT_OP_SYSCALL:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
PERF_IP_FLAG_SYSCALLRET;
case INTEL_PT_OP_SYSRET:
return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_SYSCALLRET;
default:
return 0;
}
}