linux_dsm_epyc7002/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
Ingo Molnar 3ce5aceb5d perf/core improvements and fixes:
perf record:
 
   Alexey Budankov:
 
   - Allow mixing --user-regs with --call-graph=dwarf, making sure that
     the minimal set of registers for DWARF unwinding is present in the
     set of user registers requested to be present in each sample, while
     warning the user that this may make callchains unreliable if more
     that the minimal set of registers is needed to unwind.
 
   yuzhoujian:
 
   - Add support to collect callchains from kernel or user space only,
     IOW allow setting the perf_event_attr.exclude_callchain_{kernel,user}
     bits from the command line.
 
 perf trace:
 
   Arnaldo Carvalho de Melo:
 
   - Remove x86_64 specific syscall numbers from the augmented_raw_syscalls
     BPF in-kernel collector of augmented raw_syscalls:sys_{enter,exit}
     payloads, use instead the syscall numbers obtainer either by the
     arch specific syscalltbl generators or from audit-libs.
 
   - Allow 'perf trace' to ask for the number of bytes to collect for
     string arguments, for now ask for PATH_MAX, i.e. the whole
     pathnames, which ends up being just a way to speficy which syscall
     args are pathnames and thus should be read using bpf_probe_read_str().
 
   - Skip unknown syscalls when expanding strace like syscall groups.
     This helps using the 'string' group of syscalls to work in arm64,
     where some of the syscalls present in x86_64 that deal with
     strings, for instance 'access', are deprecated and this should not
     be asked for tracing.
 
   Leo Yan:
 
   - Exit when failing to build eBPF program.
 
 perf config:
 
   Arnaldo Carvalho de Melo:
 
   - Bail out when a handler returns failure for a key-value pair. This
     helps with cases where processing a key-value pair is not just a
     matter of setting some tool specific knob, involving, for instance
     building a BPF program to then attach to the list of events 'perf
     trace' will use, e.g. augmented_raw_syscalls.c.
 
 perf.data:
 
   Kan Liang:
 
   - Read and store die ID information available in new Intel processors
     in CPUID.1F in the CPU topology written in the perf.data header.
 
 perf stat:
 
   Kan Liang:
 
   - Support per-die aggregation.
 
 Documentation:
 
   Arnaldo Carvalho de Melo:
 
   - Update perf.data documentation about the CPU_TOPOLOGY, MEM_TOPOLOGY,
     CLOCKID and DIR_FORMAT headers.
 
   Song Liu:
 
   - Add description of headers HEADER_BPF_PROG_INFO and HEADER_BPF_BTF.
 
   Leo Yan:
 
   - Update default value for llvm.clang-bpf-cmd-template in 'man perf-config'.
 
 JVMTI:
 
   Jiri Olsa:
 
   - Address gcc string overflow warning for strncpy()
 
 core:
 
   - Remove superfluous nthreads system_wide setup in perf_evsel__alloc_fd().
 
 Intel PT:
 
   Adrian Hunter:
 
   - Add support for samples to contain IPC ratio, collecting cycles
     information from CYC packets, showing the IPC info periodically, because
     Intel PT does not update the cycle count on every branch or instruction,
     the incremental values will often be zero.  When there are values, they
     will be the number of instructions and number of cycles since the last
     update, and thus represent the average IPC since the last IPC value.
 
     E.g.:
 
     # perf record --cpu 1 -m200000 -a -e intel_pt/cyc/u sleep 0.0001
     rounding mmap pages size to 1024M (262144 pages)
     [ perf record: Woken up 0 times to write data ]
     [ perf record: Captured and wrote 2.208 MB perf.data ]
     # perf script --insn-trace --xed -F+ipc,-dso,-cpu,-tid
     #
     <SNIP + add line numbering to make sense of IPC counts e.g.: (18/3)>
     1   cc1 63501.650479626: 7f5219ac27bf _int_free+0x3f   jnz 0x7f5219ac2af0       IPC: 0.81 (36/44)
     2   cc1 63501.650479626: 7f5219ac27c5 _int_free+0x45   cmp $0x1f, %rbp
     3   cc1 63501.650479626: 7f5219ac27c9 _int_free+0x49   jbe 0x7f5219ac2b00
     4   cc1 63501.650479626: 7f5219ac27cf _int_free+0x4f   test $0x8, %al
     5   cc1 63501.650479626: 7f5219ac27d1 _int_free+0x51   jnz 0x7f5219ac2b00
     6   cc1 63501.650479626: 7f5219ac27d7 _int_free+0x57   movq  0x13c58a(%rip), %rcx
     7   cc1 63501.650479626: 7f5219ac27de _int_free+0x5e   mov %rdi, %r12
     8   cc1 63501.650479626: 7f5219ac27e1 _int_free+0x61   movq  %fs:(%rcx), %rax
     9   cc1 63501.650479626: 7f5219ac27e5 _int_free+0x65   test %rax, %rax
    10   cc1 63501.650479626: 7f5219ac27e8 _int_free+0x68   jz 0x7f5219ac2821
    11   cc1 63501.650479626: 7f5219ac27ea _int_free+0x6a   leaq  -0x11(%rbp), %rdi
    12   cc1 63501.650479626: 7f5219ac27ee _int_free+0x6e   mov %rdi, %rsi
    13   cc1 63501.650479626: 7f5219ac27f1 _int_free+0x71   shr $0x4, %rsi
    14   cc1 63501.650479626: 7f5219ac27f5 _int_free+0x75   cmpq  %rsi, 0x13caf4(%rip)
    15   cc1 63501.650479626: 7f5219ac27fc _int_free+0x7c   jbe 0x7f5219ac2821
    16   cc1 63501.650479626: 7f5219ac2821 _int_free+0xa1   cmpq  0x13f138(%rip), %rbp
    17   cc1 63501.650479626: 7f5219ac2828 _int_free+0xa8   jnbe 0x7f5219ac28d8
    18   cc1 63501.650479626: 7f5219ac28d8 _int_free+0x158  testb  $0x2, 0x8(%rbx)
    19   cc1 63501.650479628: 7f5219ac28dc _int_free+0x15c  jnz 0x7f5219ac2ab0       IPC: 6.00 (18/3)
     <SNIP>
 
   - Allow using time ranges with Intel PT, i.e. these features, already
     present but not optimially usable with Intel PT, should be now:
 
         Select the second 10% time slice:
 
         $ perf script --time 10%/2
 
         Select from 0% to 10% time slice:
 
         $ perf script --time 0%-10%
 
         Select the first and second 10% time slices:
 
         $ perf script --time 10%/1,10%/2
 
         Select from 0% to 10% and 30% to 40% slices:
 
         $ perf script --time 0%-10%,30%-40%
 
 cs-etm (ARM):
 
   Mathieu Poirier:
 
   - Add support for CPU-wide trace scenarios.
 
 s390:
 
   Thomas Richter:
 
   - Fix missing kvm module load for s390.
 
   - Fix OOM error in TUI mode on s390
 
   - Support s390 diag event display when doing analysis on !s390
     architectures.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCXP/1xQAKCRCyPKLppCJ+
 J9xcAQCwOITAshE7op7HbKUPtkqiMNu+hpNa3skhxEpGHvKO0AEArpBXtuvEP8EU
 PZsp+8vcVrlZ+dZutttgvkRz25mScg8=
 =kfFb
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-5.3-20190611' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf record:

  Alexey Budankov:

  - Allow mixing --user-regs with --call-graph=dwarf, making sure that
    the minimal set of registers for DWARF unwinding is present in the
    set of user registers requested to be present in each sample, while
    warning the user that this may make callchains unreliable if more
    that the minimal set of registers is needed to unwind.

  yuzhoujian:

  - Add support to collect callchains from kernel or user space only,
    IOW allow setting the perf_event_attr.exclude_callchain_{kernel,user}
    bits from the command line.

perf trace:

  Arnaldo Carvalho de Melo:

  - Remove x86_64 specific syscall numbers from the augmented_raw_syscalls
    BPF in-kernel collector of augmented raw_syscalls:sys_{enter,exit}
    payloads, use instead the syscall numbers obtainer either by the
    arch specific syscalltbl generators or from audit-libs.

  - Allow 'perf trace' to ask for the number of bytes to collect for
    string arguments, for now ask for PATH_MAX, i.e. the whole
    pathnames, which ends up being just a way to speficy which syscall
    args are pathnames and thus should be read using bpf_probe_read_str().

  - Skip unknown syscalls when expanding strace like syscall groups.
    This helps using the 'string' group of syscalls to work in arm64,
    where some of the syscalls present in x86_64 that deal with
    strings, for instance 'access', are deprecated and this should not
    be asked for tracing.

  Leo Yan:

  - Exit when failing to build eBPF program.

perf config:

  Arnaldo Carvalho de Melo:

  - Bail out when a handler returns failure for a key-value pair. This
    helps with cases where processing a key-value pair is not just a
    matter of setting some tool specific knob, involving, for instance
    building a BPF program to then attach to the list of events 'perf
    trace' will use, e.g. augmented_raw_syscalls.c.

perf.data:

  Kan Liang:

  - Read and store die ID information available in new Intel processors
    in CPUID.1F in the CPU topology written in the perf.data header.

perf stat:

  Kan Liang:

  - Support per-die aggregation.

Documentation:

  Arnaldo Carvalho de Melo:

  - Update perf.data documentation about the CPU_TOPOLOGY, MEM_TOPOLOGY,
    CLOCKID and DIR_FORMAT headers.

  Song Liu:

  - Add description of headers HEADER_BPF_PROG_INFO and HEADER_BPF_BTF.

  Leo Yan:

  - Update default value for llvm.clang-bpf-cmd-template in 'man perf-config'.

JVMTI:

  Jiri Olsa:

  - Address gcc string overflow warning for strncpy()

core:

  - Remove superfluous nthreads system_wide setup in perf_evsel__alloc_fd().

Intel PT:

  Adrian Hunter:

  - Add support for samples to contain IPC ratio, collecting cycles
    information from CYC packets, showing the IPC info periodically, because
    Intel PT does not update the cycle count on every branch or instruction,
    the incremental values will often be zero.  When there are values, they
    will be the number of instructions and number of cycles since the last
    update, and thus represent the average IPC since the last IPC value.

    E.g.:

    # perf record --cpu 1 -m200000 -a -e intel_pt/cyc/u sleep 0.0001
    rounding mmap pages size to 1024M (262144 pages)
    [ perf record: Woken up 0 times to write data ]
    [ perf record: Captured and wrote 2.208 MB perf.data ]
    # perf script --insn-trace --xed -F+ipc,-dso,-cpu,-tid
    #
    <SNIP + add line numbering to make sense of IPC counts e.g.: (18/3)>
    1   cc1 63501.650479626: 7f5219ac27bf _int_free+0x3f   jnz 0x7f5219ac2af0       IPC: 0.81 (36/44)
    2   cc1 63501.650479626: 7f5219ac27c5 _int_free+0x45   cmp $0x1f, %rbp
    3   cc1 63501.650479626: 7f5219ac27c9 _int_free+0x49   jbe 0x7f5219ac2b00
    4   cc1 63501.650479626: 7f5219ac27cf _int_free+0x4f   test $0x8, %al
    5   cc1 63501.650479626: 7f5219ac27d1 _int_free+0x51   jnz 0x7f5219ac2b00
    6   cc1 63501.650479626: 7f5219ac27d7 _int_free+0x57   movq  0x13c58a(%rip), %rcx
    7   cc1 63501.650479626: 7f5219ac27de _int_free+0x5e   mov %rdi, %r12
    8   cc1 63501.650479626: 7f5219ac27e1 _int_free+0x61   movq  %fs:(%rcx), %rax
    9   cc1 63501.650479626: 7f5219ac27e5 _int_free+0x65   test %rax, %rax
   10   cc1 63501.650479626: 7f5219ac27e8 _int_free+0x68   jz 0x7f5219ac2821
   11   cc1 63501.650479626: 7f5219ac27ea _int_free+0x6a   leaq  -0x11(%rbp), %rdi
   12   cc1 63501.650479626: 7f5219ac27ee _int_free+0x6e   mov %rdi, %rsi
   13   cc1 63501.650479626: 7f5219ac27f1 _int_free+0x71   shr $0x4, %rsi
   14   cc1 63501.650479626: 7f5219ac27f5 _int_free+0x75   cmpq  %rsi, 0x13caf4(%rip)
   15   cc1 63501.650479626: 7f5219ac27fc _int_free+0x7c   jbe 0x7f5219ac2821
   16   cc1 63501.650479626: 7f5219ac2821 _int_free+0xa1   cmpq  0x13f138(%rip), %rbp
   17   cc1 63501.650479626: 7f5219ac2828 _int_free+0xa8   jnbe 0x7f5219ac28d8
   18   cc1 63501.650479626: 7f5219ac28d8 _int_free+0x158  testb  $0x2, 0x8(%rbx)
   19   cc1 63501.650479628: 7f5219ac28dc _int_free+0x15c  jnz 0x7f5219ac2ab0       IPC: 6.00 (18/3)
    <SNIP>

  - Allow using time ranges with Intel PT, i.e. these features, already
    present but not optimially usable with Intel PT, should be now:

        Select the second 10% time slice:

        $ perf script --time 10%/2

        Select from 0% to 10% time slice:

        $ perf script --time 0%-10%

        Select the first and second 10% time slices:

        $ perf script --time 10%/1,10%/2

        Select from 0% to 10% and 30% to 40% slices:

        $ perf script --time 0%-10%,30%-40%

cs-etm (ARM):

  Mathieu Poirier:

  - Add support for CPU-wide trace scenarios.

s390:

  Thomas Richter:

  - Fix missing kvm module load for s390.

  - Fix OOM error in TUI mode on s390

  - Support s390 diag event display when doing analysis on !s390
    architectures.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-06-17 20:48:14 +02:00

133 lines
3.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* intel_pt_decoder.h: Intel Processor Trace support
* Copyright (c) 2013-2014, Intel Corporation.
*/
#ifndef INCLUDE__INTEL_PT_DECODER_H__
#define INCLUDE__INTEL_PT_DECODER_H__
#include <stdint.h>
#include <stddef.h>
#include <stdbool.h>
#include "intel-pt-insn-decoder.h"
#define INTEL_PT_IN_TX (1 << 0)
#define INTEL_PT_ABORT_TX (1 << 1)
#define INTEL_PT_ASYNC (1 << 2)
#define INTEL_PT_FUP_IP (1 << 3)
enum intel_pt_sample_type {
INTEL_PT_BRANCH = 1 << 0,
INTEL_PT_INSTRUCTION = 1 << 1,
INTEL_PT_TRANSACTION = 1 << 2,
INTEL_PT_PTW = 1 << 3,
INTEL_PT_MWAIT_OP = 1 << 4,
INTEL_PT_PWR_ENTRY = 1 << 5,
INTEL_PT_EX_STOP = 1 << 6,
INTEL_PT_PWR_EXIT = 1 << 7,
INTEL_PT_CBR_CHG = 1 << 8,
INTEL_PT_TRACE_BEGIN = 1 << 9,
INTEL_PT_TRACE_END = 1 << 10,
};
enum intel_pt_period_type {
INTEL_PT_PERIOD_NONE,
INTEL_PT_PERIOD_INSTRUCTIONS,
INTEL_PT_PERIOD_TICKS,
INTEL_PT_PERIOD_MTC,
};
enum {
INTEL_PT_ERR_NOMEM = 1,
INTEL_PT_ERR_INTERN,
INTEL_PT_ERR_BADPKT,
INTEL_PT_ERR_NODATA,
INTEL_PT_ERR_NOINSN,
INTEL_PT_ERR_MISMAT,
INTEL_PT_ERR_OVR,
INTEL_PT_ERR_LOST,
INTEL_PT_ERR_UNK,
INTEL_PT_ERR_NELOOP,
INTEL_PT_ERR_MAX,
};
enum intel_pt_param_flags {
/*
* FUP packet can contain next linear instruction pointer instead of
* current linear instruction pointer.
*/
INTEL_PT_FUP_WITH_NLIP = 1 << 0,
};
struct intel_pt_state {
enum intel_pt_sample_type type;
int err;
uint64_t from_ip;
uint64_t to_ip;
uint64_t cr3;
uint64_t tot_insn_cnt;
uint64_t tot_cyc_cnt;
uint64_t timestamp;
uint64_t est_timestamp;
uint64_t trace_nr;
uint64_t ptw_payload;
uint64_t mwait_payload;
uint64_t pwre_payload;
uint64_t pwrx_payload;
uint64_t cbr_payload;
uint32_t flags;
enum intel_pt_insn_op insn_op;
int insn_len;
char insn[INTEL_PT_INSN_BUF_SZ];
};
struct intel_pt_insn;
struct intel_pt_buffer {
const unsigned char *buf;
size_t len;
bool consecutive;
uint64_t ref_timestamp;
uint64_t trace_nr;
};
typedef int (*intel_pt_lookahead_cb_t)(struct intel_pt_buffer *, void *);
struct intel_pt_params {
int (*get_trace)(struct intel_pt_buffer *buffer, void *data);
int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
uint64_t max_insn_cnt, void *data);
bool (*pgd_ip)(uint64_t ip, void *data);
int (*lookahead)(void *data, intel_pt_lookahead_cb_t cb, void *cb_data);
void *data;
bool return_compression;
bool branch_enable;
uint64_t period;
enum intel_pt_period_type period_type;
unsigned max_non_turbo_ratio;
unsigned int mtc_period;
uint32_t tsc_ctc_ratio_n;
uint32_t tsc_ctc_ratio_d;
enum intel_pt_param_flags flags;
};
struct intel_pt_decoder;
struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params);
void intel_pt_decoder_free(struct intel_pt_decoder *decoder);
const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
int intel_pt_fast_forward(struct intel_pt_decoder *decoder, uint64_t timestamp);
unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
unsigned char *buf_b, size_t len_b,
bool have_tsc, bool *consecutive);
int intel_pt__strerror(int code, char *buf, size_t buflen);
#endif