hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

perf/core improvements and fixes: 

perf trace:
 
 - Augment the payload of syscall entry/exit tracepoints with the contents
   of pointer arguments, such as the "filename" argument to the "open"
   syscall or the 'struct sockaddr *' argument to the 'connect' syscall.
 
   This is done using a BPF program that gets compiled and attached to
   various syscalls:sys_enter_NAME tracepoints, copying via a BPF map and
   "bpf-output" perf event the raw_syscalls:sys_enter tracepoint payload +
   the contents of pointer arguments using the "probe_read", "probe_read_str"
   and "perf_event_output" BPF functions.
 
   The 'perf trace' codebase now just processes these augmented tracepoints
   using the existing beautifiers that now check if there is more in the
   perf_sample->raw_data than what is expected for a normal syscall enter
   tracepoint (the common preamble, syscall id, up to six parameters),
   using that with hand crafted struct beautifiers.
 
   This is just to show how to augment the existing tracepoints, work will
   be done to use DWARF or BTF info to do the pretty-printing and to create
   the collectors.
 
   For now this is done using an example restricted C BPF program, but the
   end goal is to have this all autogenerated and done transparently.
 
   Its still useful to have this example as one can use it as an skeleton and
   write more involved filters, see the etcsnoop.c BPF example, for instance.
 
   E.g.:
 
   # cd tools/perf/examples/bpf/
   # perf trace -e augmented_syscalls.c ping -c 1 ::1
      0.000 ( 0.008 ms): openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
      0.020 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
      0.051 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
      0.076 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
      0.106 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
      0.136 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
      0.194 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
      0.224 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
      0.252 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
      0.275 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
      0.730 ( 0.007 ms): open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
   PING ::1(::1) 56 data bytes
      0.834 ( 0.008 ms): connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
   64 bytes from ::1: icmp_seq=1 ttl=64 time=0.032 ms
 
   --- ::1 ping statistics ---
   1 packets transmitted, 1 received, 0% packet loss, time 0ms
   rtt min/avg/max/mdev = 0.032/0.032/0.032/0.000 ms
      0.914 ( 0.036 ms): sendto(fd: 4<socket:[843044]>, buff: 0x55b5e52e9720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
   #
 
   Use 'perf trace -e augmented_syscalls.c,close ping -c 1 ::1' to see the
   'close' calls as well, as it is not one of the syscalls augmented in that .c
   file.
 
   (Arnaldo Carvalho de Melo)
 
 - Alias 'umount' to 'umount2' (Benjamin Peterson)
 
 perf stat: (Jiri Olsa)
 
 - Make many builtin-stat.c functions generic, moving display functions
   to a separate file, prep work for adding the ability to store/display
   stat data in perf record/top.
 
 perf annotate: (Kim Phillips)
 
 - Handle arm64 move instructions
 
 perf report: (Thomas Richter):
 
 - Create auxiliary trace data files for s390
 
 libtraceevent: (Tzvetomir Stoyanov (VMware)):
 
 - Split trace-seq related APIs in a separate header file.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCW5BHbgAKCRCyPKLppCJ+
 J6WGAQDoPezUDbL8azCcscZZaaT4W63oAyVizOdy4qUIw5D2BAD+P2bYTmW3EKeO
 d3FXWqtpMRNR0CFhWPi57XpJiia0oA0=
 =ICRn
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-4.20-20180905' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

perf trace:

- Augment the payload of syscall entry/exit tracepoints with the contents
  of pointer arguments, such as the "filename" argument to the "open"
  syscall or the 'struct sockaddr *' argument to the 'connect' syscall.

  This is done using a BPF program that gets compiled and attached to
  various syscalls:sys_enter_NAME tracepoints, copying via a BPF map and
  "bpf-output" perf event the raw_syscalls:sys_enter tracepoint payload +
  the contents of pointer arguments using the "probe_read", "probe_read_str"
  and "perf_event_output" BPF functions.

  The 'perf trace' codebase now just processes these augmented tracepoints
  using the existing beautifiers that now check if there is more in the
  perf_sample->raw_data than what is expected for a normal syscall enter
  tracepoint (the common preamble, syscall id, up to six parameters),
  using that with hand crafted struct beautifiers.

  This is just to show how to augment the existing tracepoints, work will
  be done to use DWARF or BTF info to do the pretty-printing and to create
  the collectors.

  For now this is done using an example restricted C BPF program, but the
  end goal is to have this all autogenerated and done transparently.

  Its still useful to have this example as one can use it as an skeleton and
  write more involved filters, see the etcsnoop.c BPF example, for instance.

  E.g.:

  # cd tools/perf/examples/bpf/
  # perf trace -e augmented_syscalls.c ping -c 1 ::1
     0.000 ( 0.008 ms): openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.020 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
     0.051 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
     0.076 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
     0.106 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
     0.136 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
     0.194 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.224 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
     0.252 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
     0.275 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
     0.730 ( 0.007 ms): open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
  PING ::1(::1) 56 data bytes
     0.834 ( 0.008 ms): connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.032 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.032/0.032/0.032/0.000 ms
     0.914 ( 0.036 ms): sendto(fd: 4<socket:[843044]>, buff: 0x55b5e52e9720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
  #

  Use 'perf trace -e augmented_syscalls.c,close ping -c 1 ::1' to see the
  'close' calls as well, as it is not one of the syscalls augmented in that .c
  file.

  (Arnaldo Carvalho de Melo)

- Alias 'umount' to 'umount2' (Benjamin Peterson)

perf stat: (Jiri Olsa)

- Make many builtin-stat.c functions generic, moving display functions
  to a separate file, prep work for adding the ability to store/display
  stat data in perf record/top.

perf annotate: (Kim Phillips)

- Handle arm64 move instructions

perf report: (Thomas Richter):

- Create auxiliary trace data files for s390

libtraceevent: (Tzvetomir Stoyanov (VMware)):

- Split trace-seq related APIs in a separate header file.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Thomas Gleixner 2018-09-06 14:56:44 +02:00
parent 60c1f89241 1632936480
commit bda58ee8f8
55 changed files with 2543 additions and 1573 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
kernel/events/core.c
View File

@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp,
_perf_event_disable(bp);
err = modify_user_hw_breakpoint_check(bp, attr, true);
if (err) {
if (!bp->attr.disabled)
_perf_event_enable(bp);
return err;
}
if (!attr->disabled)
if (!bp->attr.disabled)
_perf_event_enable(bp);
return 0;
return err;
}
static int perf_event_modify_attr(struct perf_event *event,

13
kernel/events/hw_breakpoint.c
View File

@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
*/
int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
{
int err;
/*
* modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
* will not be possible to raise IPIs that invoke __perf_event_disable.
@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
else
perf_event_disable(bp);
if (!attr->disabled) {
int err = modify_user_hw_breakpoint_check(bp, attr, false);
err = modify_user_hw_breakpoint_check(bp, attr, false);
if (err)
return err;
if (!bp->attr.disabled)
perf_event_enable(bp);
bp->attr.disabled = 0;
}
return 0;
return err;
}
EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);

1
tools/lib/traceevent/event-parse.c
View File

@ -24,6 +24,7 @@
#include <netinet/in.h>
#include "event-parse.h"
#include "event-utils.h"
#include "trace-seq.h"
static const char *input_buf;
static unsigned long long input_buf_ptr;

46
tools/lib/traceevent/event-parse.h
View File

@ -26,17 +26,12 @@
#include <regex.h>
#include <string.h>
#include "trace-seq.h"
#ifndef __maybe_unused
#define __maybe_unused __attribute__((unused))
#endif
/* ----------------------- trace_seq ----------------------- */
#ifndef TRACE_SEQ_BUF_SIZE
#define TRACE_SEQ_BUF_SIZE 4096
#endif
#ifndef DEBUG_RECORD
#define DEBUG_RECORD 0
#endif
@ -59,43 +54,6 @@ struct tep_record {
#endif
};
enum trace_seq_fail {
TRACE_SEQ__GOOD,
TRACE_SEQ__BUFFER_POISONED,
TRACE_SEQ__MEM_ALLOC_FAILED,
};
/*
* Trace sequences are used to allow a function to call several other functions
* to create a string of data to use (up to a max of PAGE_SIZE).
*/
struct trace_seq {
char *buffer;
unsigned int buffer_size;
unsigned int len;
unsigned int readpos;
enum trace_seq_fail state;
};
void trace_seq_init(struct trace_seq *s);
void trace_seq_reset(struct trace_seq *s);
void trace_seq_destroy(struct trace_seq *s);
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
__attribute__ ((format (printf, 2, 0)));
extern int trace_seq_puts(struct trace_seq *s, const char *str);
extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
extern void trace_seq_terminate(struct trace_seq *s);
extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
extern int trace_seq_do_printf(struct trace_seq *s);
/* ----------------------- pevent ----------------------- */
struct tep_handle;

1
tools/lib/traceevent/event-plugin.c
View File

@ -15,6 +15,7 @@
#include <dirent.h>
#include "event-parse.h"
#include "event-utils.h"
#include "trace-seq.h"
#define LOCAL_PLUGIN_DIR ".traceevent/plugins"

1
tools/lib/traceevent/plugin_function.c
View File

@ -23,6 +23,7 @@
#include "event-parse.h"
#include "event-utils.h"
#include "trace-seq.h"
static struct func_stack {
int size;

1
tools/lib/traceevent/plugin_hrtimer.c
View File

@ -23,6 +23,7 @@
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
static int timer_expire_handler(struct trace_seq *s,
struct tep_record *record,

1
tools/lib/traceevent/plugin_jbd2.c
View File

@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
#define MINORBITS 20
#define MINORMASK ((1U << MINORBITS) - 1)

1
tools/lib/traceevent/plugin_kmem.c
View File

@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
static int call_site_handler(struct trace_seq *s, struct tep_record *record,
struct event_format *event, void *context)

1
tools/lib/traceevent/plugin_kvm.c
View File

@ -23,6 +23,7 @@
#include <stdint.h>
#include "event-parse.h"
#include "trace-seq.h"
#ifdef HAVE_UDIS86

1
tools/lib/traceevent/plugin_mac80211.c
View File

@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
#define INDENT 65

1
tools/lib/traceevent/plugin_sched_switch.c
View File

@ -22,6 +22,7 @@
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
static void write_state(struct trace_seq *s, int val)
{

1
tools/lib/traceevent/plugin_scsi.c
View File

@ -3,6 +3,7 @@
#include <string.h>
#include <inttypes.h>
#include "event-parse.h"
#include "trace-seq.h"
typedef unsigned long sector_t;
typedef uint64_t u64;

1
tools/lib/traceevent/plugin_xen.c
View File

@ -3,6 +3,7 @@
#include <stdlib.h>
#include <string.h>
#include "event-parse.h"
#include "trace-seq.h"
#define __HYPERVISOR_set_trap_table 0
#define __HYPERVISOR_mmu_update 1

2
tools/lib/traceevent/trace-seq.c
View File

@ -3,6 +3,8 @@
* Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
#include "trace-seq.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

55
tools/lib/traceevent/trace-seq.h Normal file
View File

@ -0,0 +1,55 @@
// SPDX-License-Identifier: LGPL-2.1
/*
* Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
#ifndef _TRACE_SEQ_H
#define _TRACE_SEQ_H
#include <stdarg.h>
#include <stdio.h>
/* ----------------------- trace_seq ----------------------- */
#ifndef TRACE_SEQ_BUF_SIZE
#define TRACE_SEQ_BUF_SIZE 4096
#endif
enum trace_seq_fail {
TRACE_SEQ__GOOD,
TRACE_SEQ__BUFFER_POISONED,
TRACE_SEQ__MEM_ALLOC_FAILED,
};
/*
* Trace sequences are used to allow a function to call several other functions
* to create a string of data to use (up to a max of PAGE_SIZE).
*/
struct trace_seq {
char *buffer;
unsigned int buffer_size;
unsigned int len;
unsigned int readpos;
enum trace_seq_fail state;
};
void trace_seq_init(struct trace_seq *s);
void trace_seq_reset(struct trace_seq *s);
void trace_seq_destroy(struct trace_seq *s);
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
__attribute__ ((format (printf, 2, 0)));
extern int trace_seq_puts(struct trace_seq *s, const char *str);
extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
extern void trace_seq_terminate(struct trace_seq *s);
extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
extern int trace_seq_do_printf(struct trace_seq *s);
#endif /* _TRACE_SEQ_H */

16
tools/perf/Makefile.perf
View File

@ -777,14 +777,14 @@ endif
$(call QUIET_INSTALL, libexec) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
ifndef NO_LIBBPF
$(call QUIET_INSTALL, lib) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
$(call QUIET_INSTALL, include/bpf) \
$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
$(call QUIET_INSTALL, lib) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
$(call QUIET_INSTALL, examples/bpf) \
$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
$(call QUIET_INSTALL, bpf-headers) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
$(call QUIET_INSTALL, bpf-examples) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
endif
$(call QUIET_INSTALL, perf-archive) \
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'

5
tools/perf/arch/arm64/Makefile
View File

@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
out := $(OUTPUT)arch/arm64/include/generated/asm
header := $(out)/syscalls.c
sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
incpath := $(srctree)/tools
sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
systbl := $(sysprf)/mksyscalltbl
@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl
_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
$(header): $(sysdef) $(systbl)
$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
clean::
$(call QUIET_CLEAN, arm64) $(RM) $(header)

59
tools/perf/arch/arm64/annotate/instructions.c
View File

@ -8,6 +8,63 @@ struct arm64_annotate {
jump_insn;
};
static int arm64_mov__parse(struct arch *arch __maybe_unused,
struct ins_operands *ops,
struct map_symbol *ms __maybe_unused)
{
char *s = strchr(ops->raw, ','), *target, *endptr;
if (s == NULL)
return -1;
*s = '\0';
ops->source.raw = strdup(ops->raw);
*s = ',';
if (ops->source.raw == NULL)
return -1;
target = ++s;
ops->target.raw = strdup(target);
if (ops->target.raw == NULL)
goto out_free_source;
ops->target.addr = strtoull(target, &endptr, 16);
if (endptr == target)
goto out_free_target;
s = strchr(endptr, '<');
if (s == NULL)
goto out_free_target;
endptr = strchr(s + 1, '>');
if (endptr == NULL)
goto out_free_target;
*endptr = '\0';
*s = ' ';
ops->target.name = strdup(s);
*s = '<';
*endptr = '>';
if (ops->target.name == NULL)
goto out_free_target;
return 0;
out_free_target:
zfree(&ops->target.raw);
out_free_source:
zfree(&ops->source.raw);
return -1;
}
static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
struct ins_operands *ops);
static struct ins_ops arm64_mov_ops = {
.parse = arm64_mov__parse,
.scnprintf = mov__scnprintf,
};
static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
{
struct arm64_annotate *arm = arch->priv;
@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
else if (!strcmp(name, "ret"))
ops = &ret_ops;
else
return NULL;
ops = &arm64_mov_ops;
arch__associate_ins_ops(arch, name, ops);
return ops;

6
tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
View File

@ -11,7 +11,8 @@
gcc=$1
hostcc=$2
input=$3
incpath=$3
input=$4
if ! test -r $input; then
echo "Could not read input file" >&2
@ -28,7 +29,6 @@ create_table_from_c()
cat <<-_EoHEADER
#include <stdio.h>
#define __ARCH_WANT_RENAMEAT
#include "$input"
int main(int argc, char *argv[])
{
@ -42,7 +42,7 @@ create_table_from_c()
printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
printf "}\n"
} | $hostcc -o $create_table_exe -x c -
} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
$create_table_exe

4
tools/perf/arch/powerpc/util/sym-handling.c
View File

@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
#endif
#if !defined(_CALL_ELF) || _CALL_ELF != 2
int arch__choose_best_symbol(struct symbol *syma,
struct symbol *symb __maybe_unused)
{
char *sym = syma->name;
#if !defined(_CALL_ELF) || _CALL_ELF != 2
/* Skip over any initial dot */
if (*sym == '.')
sym++;
#endif
/* Avoid "SyS" kernel syscall aliases */
if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma,
return SYMBOL_A;
}
#if !defined(_CALL_ELF) || _CALL_ELF != 2
/* Allow matching against dot variants */
int arch__compare_symbol_names(const char *namea, const char *nameb)
{

2
tools/perf/arch/s390/annotate/instructions.c
View File

@ -100,8 +100,6 @@ out_free_source:
return -1;
}
static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
struct ins_operands *ops);
static struct ins_ops s390_mov_ops = {
.parse = s390_mov__parse,

1
tools/perf/arch/x86/include/arch-tests.h
View File

@ -9,6 +9,7 @@ struct test;
int test__rdpmc(struct test *test __maybe_unused, int subtest);
int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
int test__insn_x86(struct test *test __maybe_unused, int subtest);
int test__bp_modify(struct test *test, int subtest);
#ifdef HAVE_DWARF_UNWIND_SUPPORT
struct thread;

1
tools/perf/arch/x86/tests/Build
View File

@ -5,3 +5,4 @@ libperf-y += arch-tests.o
libperf-y += rdpmc.o
libperf-y += perf-time-to-tsc.o
libperf-$(CONFIG_AUXTRACE) += insn-x86.o
libperf-$(CONFIG_X86_64) += bp-modify.o

6
tools/perf/arch/x86/tests/arch-tests.c
View File

@ -23,6 +23,12 @@ struct test arch_tests[] = {
.desc = "x86 instruction decoder - new instructions",
.func = test__insn_x86,
},
#endif
#if defined(__x86_64__)
{
.desc = "x86 bp modify",
.func = test__bp_modify,
},
#endif
{
.func = NULL,

213
tools/perf/arch/x86/tests/bp-modify.c Normal file
View File

@ -0,0 +1,213 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <sys/user.h>
#include <syscall.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ptrace.h>
#include <asm/ptrace.h>
#include <errno.h>
#include "debug.h"
#include "tests/tests.h"
#include "arch-tests.h"
static noinline int bp_1(void)
{
pr_debug("in %s\n", __func__);
return 0;
}
static noinline int bp_2(void)
{
pr_debug("in %s\n", __func__);
return 0;
}
static int spawn_child(void)
{
int child = fork();
if (child == 0) {
/*
* The child sets itself for as tracee and
* waits in signal for parent to trace it,
* then it calls bp_1 and quits.
*/
int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL);
if (err) {
pr_debug("failed to PTRACE_TRACEME\n");
exit(1);
}
raise(SIGCONT);
bp_1();
exit(0);
}
return child;
}
/*
* This tests creates HW breakpoint, tries to
* change it and checks it was properly changed.
*/
static int bp_modify1(void)
{
pid_t child;
int status;
unsigned long rip = 0, dr7 = 1;
child = spawn_child();
waitpid(child, &status, 0);
if (WIFEXITED(status)) {
pr_debug("tracee exited prematurely 1\n");
return TEST_FAIL;
}
/*
* The parent does following steps:
* - creates a new breakpoint (id 0) for bp_2 function
* - changes that breakponit to bp_1 function
* - waits for the breakpoint to hit and checks
* it has proper rip of bp_1 function
* - detaches the child
*/
if (ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[0]), bp_2)) {
pr_debug("failed to set breakpoint, 1st time: %s\n",
strerror(errno));
goto out;
}
if (ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[0]), bp_1)) {
pr_debug("failed to set breakpoint, 2nd time: %s\n",
strerror(errno));
goto out;
}
if (ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[7]), dr7)) {
pr_debug("failed to set dr7: %s\n", strerror(errno));
goto out;
}
if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
goto out;
}
waitpid(child, &status, 0);
if (WIFEXITED(status)) {
pr_debug("tracee exited prematurely 2\n");
return TEST_FAIL;
}
rip = ptrace(PTRACE_PEEKUSER, child,
offsetof(struct user_regs_struct, rip), NULL);
if (rip == (unsigned long) -1) {
pr_debug("failed to PTRACE_PEEKUSER: %s\n",
strerror(errno));
goto out;
}
pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
out:
if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
return TEST_FAIL;
}
return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
}
/*
* This tests creates HW breakpoint, tries to
* change it to bogus value and checks the original
* breakpoint is hit.
*/
static int bp_modify2(void)
{
pid_t child;
int status;
unsigned long rip = 0, dr7 = 1;
child = spawn_child();
waitpid(child, &status, 0);
if (WIFEXITED(status)) {
pr_debug("tracee exited prematurely 1\n");
return TEST_FAIL;
}
/*
* The parent does following steps:
* - creates a new breakpoint (id 0) for bp_1 function
* - tries to change that breakpoint to (-1) address
* - waits for the breakpoint to hit and checks
* it has proper rip of bp_1 function
* - detaches the child
*/
if (ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[0]), bp_1)) {
pr_debug("failed to set breakpoint: %s\n",
strerror(errno));
goto out;
}
if (ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[7]), dr7)) {
pr_debug("failed to set dr7: %s\n", strerror(errno));
goto out;
}
if (!ptrace(PTRACE_POKEUSER, child,
offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) {
pr_debug("failed, breakpoint set to bogus address\n");
goto out;
}
if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
goto out;
}
waitpid(child, &status, 0);
if (WIFEXITED(status)) {
pr_debug("tracee exited prematurely 2\n");
return TEST_FAIL;
}
rip = ptrace(PTRACE_PEEKUSER, child,
offsetof(struct user_regs_struct, rip), NULL);
if (rip == (unsigned long) -1) {
pr_debug("failed to PTRACE_PEEKUSER: %s\n",
strerror(errno));
goto out;
}
pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
out:
if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
return TEST_FAIL;
}
return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
}
int test__bp_modify(struct test *test __maybe_unused,
int subtest __maybe_unused)
{
TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2());
return 0;
}

2
tools/perf/builtin-record.c
View File

@ -758,7 +758,7 @@ static int record__synthesize(struct record *rec, bool tail)
* We need to synthesize events first, because some
* features works on top of them (on report side).
*/
err = perf_event__synthesize_attrs(tool, session,
err = perf_event__synthesize_attrs(tool, rec->evlist,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");

8
tools/perf/builtin-script.c
View File

@ -1544,7 +1544,8 @@ struct metric_ctx {
FILE *fp;
};
static void script_print_metric(void *ctx, const char *color,
static void script_print_metric(struct perf_stat_config *config __maybe_unused,
void *ctx, const char *color,
const char *fmt,
const char *unit, double val)
{
@ -1562,7 +1563,8 @@ static void script_print_metric(void *ctx, const char *color,
fprintf(mctx->fp, " %s\n", unit);
}
static void script_new_line(void *ctx)
static void script_new_line(struct perf_stat_config *config __maybe_unused,
void *ctx)
{
struct metric_ctx *mctx = ctx;
@ -1608,7 +1610,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
evsel_script(evsel)->val = val;
if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
for_each_group_member (ev2, evsel->leader) {
perf_stat__print_shadow_stats(ev2,
perf_stat__print_shadow_stats(&stat_config, ev2,
evsel_script(ev2)->val,
sample->cpu,
&ctx,

1440
tools/perf/builtin-stat.c
View File

File diff suppressed because it is too large Load Diff

163
tools/perf/builtin-trace.c
View File

@ -288,6 +288,13 @@ static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
}
static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
{
struct syscall_tp *sc = evsel->priv;
return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
}
static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
{
evsel->priv = malloc(sizeof(struct syscall_tp));
@ -498,16 +505,6 @@ static const char *clockid[] = {
};
static DEFINE_STRARRAY(clockid);
static const char *socket_families[] = {
"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
"ALG", "NFC", "VSOCK",
};
static DEFINE_STRARRAY(socket_families);
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
struct syscall_arg *arg)
{
@ -631,6 +628,8 @@ static struct syscall_fmt {
} syscall_fmts[] = {
{ .name = "access",
.arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, },
{ .name = "bind",
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
{ .name = "bpf",
.arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
{ .name = "brk", .hexret = true,
@ -645,6 +644,8 @@ static struct syscall_fmt {
[4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, },
{ .name = "close",
.arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
{ .name = "connect",
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
{ .name = "epoll_ctl",
.arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
{ .name = "eventfd2",
@ -801,7 +802,8 @@ static struct syscall_fmt {
{ .name = "sendmsg",
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "sendto",
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
[4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
{ .name = "set_tid_address", .errpid = true, },
{ .name = "setitimer",
.arg = { [0] = STRARRAY(which, itimers), }, },
@ -830,6 +832,7 @@ static struct syscall_fmt {
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "tkill",
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "umount2", .alias = "umount", },
{ .name = "uname", .alias = "newuname", },
{ .name = "unlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@ -856,10 +859,12 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
/*
* is_exit: is this "exit" or "exit_group"?
* is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
* args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
*/
struct syscall {
struct event_format *tp_format;
int nr_args;
int args_size;
bool is_exit;
bool is_open;
struct format_field *args;
@ -1095,11 +1100,21 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf,
ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
}
static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
{
struct augmented_arg *augmented_arg = arg->augmented.args;
return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
}
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
struct syscall_arg *arg)
{
unsigned long ptr = arg->val;
if (arg->augmented.args)
return syscall_arg__scnprintf_augmented_string(arg, bf, size);
if (!arg->trace->vfs_getname)
return scnprintf(bf, size, "%#x", ptr);
@ -1142,11 +1157,9 @@ static void sig_handler(int sig)
interrupted = sig == SIGINT;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
{
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
printed += fprintf_duration(duration, duration_calculated, fp);
size_t printed = 0;
if (trace->multiple_threads) {
if (trace->show_comm)
@ -1157,6 +1170,14 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
return printed;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
{
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
printed += fprintf_duration(duration, duration_calculated, fp);
return printed + trace__fprintf_comm_tid(trace, thread, fp);
}
static int trace__process_event(struct trace *trace, struct machine *machine,
union perf_event *event, struct perf_sample *sample)
{
@ -1258,10 +1279,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
static int syscall__set_arg_fmts(struct syscall *sc)
{
struct format_field *field;
struct format_field *field, *last_field = NULL;
int idx = 0, len;
for (field = sc->args; field; field = field->next, ++idx) {
last_field = field;
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
continue;
@ -1292,6 +1315,9 @@ static int syscall__set_arg_fmts(struct syscall *sc)
}
}
if (last_field)
sc->args_size = last_field->offset + last_field->size;
return 0;
}
@ -1472,14 +1498,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
}
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
unsigned char *args, struct trace *trace,
struct thread *thread)
unsigned char *args, void *augmented_args, int augmented_args_size,
struct trace *trace, struct thread *thread)
{
size_t printed = 0;
unsigned long val;
u8 bit = 1;
struct syscall_arg arg = {
.args = args,
.augmented = {
.size = augmented_args_size,
.args = augmented_args,
},
.idx = 0,
.mask = 0,
.trace = trace,
@ -1654,6 +1684,17 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
return printed;
}
static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
{
void *augmented_args = NULL;
*augmented_args_size = sample->raw_size - sc->args_size;
if (*augmented_args_size > 0)
augmented_args = sample->raw_data + sc->args_size;
return augmented_args;
}
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
@ -1663,6 +1704,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
size_t printed = 0;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
int augmented_args_size = 0;
void *augmented_args = NULL;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
@ -1686,13 +1729,24 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
trace__printf_interrupted_entry(trace);
/*
* If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
* arguments, even if the syscall being handled, say "openat", uses only 4 arguments
* this breaks syscall__augmented_args() check for augmented args, as we calculate
* syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
* so when handling, say the openat syscall, we end up getting 6 args for the
* raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
* thinking that the extra 2 u64 args are the augmented filename, so just check
* here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
*/
if (evsel != trace->syscalls.events.sys_enter)
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
ttrace->entry_time = sample->time;
msg = ttrace->entry_str;
printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
args, trace, thread);
args, augmented_args, augmented_args_size, trace, thread);
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
@ -1723,7 +1777,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
char msg[1024];
void *args;
void *args, *augmented_args = NULL;
int augmented_args_size;
if (sc == NULL)
return -1;
@ -1738,7 +1793,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
fprintf(trace->output, "%s", msg);
err = 0;
out_put:
@ -2022,6 +2078,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
int callchain_ret = 0;
if (sample->callchain) {
@ -2039,13 +2096,31 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
if (trace->trace_syscalls)
fprintf(trace->output, "( ): ");
if (thread)
trace__fprintf_comm_tid(trace, thread, trace->output);
if (evsel == trace->syscalls.events.augmented) {
int id = perf_evsel__sc_tp_uint(evsel, id, sample);
struct syscall *sc = trace__syscall_info(trace, evsel, id);
if (sc) {
fprintf(trace->output, "%s(", sc->name);
trace__fprintf_sys_enter(trace, evsel, sample);
fputc(')', trace->output);
goto newline;
}
/*
* XXX: Not having the associated syscall info or not finding/adding
* the thread should never happen, but if it does...
* fall thru and print it as a bpf_output event.
*/
}
fprintf(trace->output, "%s:", evsel->name);
if (perf_evsel__is_bpf_output(evsel)) {
if (evsel == trace->syscalls.events.augmented)
trace__fprintf_sys_enter(trace, evsel, sample);
else
bpf_output__fprintf(trace, sample);
bpf_output__fprintf(trace, sample);
} else if (evsel->tp_format) {
if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
trace__fprintf_sys_enter(trace, evsel, sample)) {
@ -2055,12 +2130,14 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
}
}
newline:
fprintf(trace->output, "\n");
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
thread__put(thread);
out:
return 0;
}
@ -3276,12 +3353,8 @@ int cmd_trace(int argc, const char **argv)
goto out;
}
if (evsel) {
if (perf_evsel__init_augmented_syscall_tp(evsel) ||
perf_evsel__init_augmented_syscall_tp_args(evsel))
goto out;
if (evsel)
trace.syscalls.events.augmented = evsel;
}
err = bpf__setup_stdout(trace.evlist);
if (err) {
@ -3326,6 +3399,34 @@ int cmd_trace(int argc, const char **argv)
}
}
/*
* If we are augmenting syscalls, then combine what we put in the
* __augmented_syscalls__ BPF map with what is in the
* syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
* combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
*
* We'll switch to look at two BPF maps, one for sys_enter and the
* other for sys_exit when we start augmenting the sys_exit paths with
* buffers that are being copied from kernel to userspace, think 'read'
* syscall.
*/
if (trace.syscalls.events.augmented) {
evsel = trace.syscalls.events.augmented;
if (perf_evsel__init_augmented_syscall_tp(evsel) ||
perf_evsel__init_augmented_syscall_tp_args(evsel))
goto out;
evsel->handler = trace__sys_enter;
evlist__for_each_entry(trace.evlist, evsel) {
if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
perf_evsel__init_augmented_syscall_tp(evsel);
perf_evsel__init_augmented_syscall_tp_ret(evsel);
evsel->handler = trace__sys_exit;
}
}
}
if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
return trace__record(&trace, argc-1, &argv[1]);

154
tools/perf/examples/bpf/augmented_syscalls.c
View File

@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Augment the openat syscall with the contents of the filename pointer argument.
* Augment syscalls with the contents of the pointer arguments.
*
* Test it with:
*
@ -10,15 +10,14 @@
* the last one should be the one for '/etc/passwd'.
*
* This matches what is marshalled into the raw_syscall:sys_enter payload
* expected by the 'perf trace' beautifiers, and can be used by them unmodified,
* which will be done as that feature is implemented in the next csets, for now
* it will appear in a dump done by the default tracepoint handler in 'perf trace',
* that uses bpf_output__fprintf() to just dump those contents, as done with
* the bpf-output event associated with the __bpf_output__ map declared in
* tools/perf/include/bpf/stdio.h.
* expected by the 'perf trace' beautifiers, and can be used by them, that will
* check if perf_sample->raw_data is more than what is expected for each
* syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
* contents of pointer arguments.
*/
#include <stdio.h>
#include <linux/socket.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
@ -27,6 +26,44 @@ struct bpf_map SEC("maps") __augmented_syscalls__ = {
.max_entries = __NR_CPUS__,
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
long syscall_nr;
long ret;
};
struct augmented_filename {
unsigned int size;
int reserved;
char value[256];
};
#define augmented_filename_syscall(syscall) \
struct augmented_enter_##syscall##_args { \
struct syscall_enter_##syscall##_args args; \
struct augmented_filename filename; \
}; \
int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
{ \
struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \
unsigned int len = sizeof(augmented_args); \
probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \
sizeof(augmented_args.filename.value), \
args->filename_ptr); \
if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { \
len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \
len &= sizeof(augmented_args.filename.value) - 1; \
} \
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
&augmented_args, len); \
return 0; \
} \
int syscall_exit(syscall)(struct syscall_exit_args *args) \
{ \
return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
}
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
@ -36,20 +73,101 @@ struct syscall_enter_openat_args {
long mode;
};
struct augmented_enter_openat_args {
struct syscall_enter_openat_args args;
char filename[64];
augmented_filename_syscall(openat);
struct syscall_enter_open_args {
unsigned long long common_tp_fields;
long syscall_nr;
char *filename_ptr;
long flags;
long mode;
};
int syscall_enter(openat)(struct syscall_enter_openat_args *args)
{
struct augmented_enter_openat_args augmented_args;
augmented_filename_syscall(open);
probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
&augmented_args, sizeof(augmented_args));
return 1;
struct syscall_enter_inotify_add_watch_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
char *filename_ptr;
long mask;
};
augmented_filename_syscall(inotify_add_watch);
struct statbuf;
struct syscall_enter_newstat_args {
unsigned long long common_tp_fields;
long syscall_nr;
char *filename_ptr;
struct stat *statbuf;
};
augmented_filename_syscall(newstat);
#ifndef _K_SS_MAXSIZE
#define _K_SS_MAXSIZE 128
#endif
#define augmented_sockaddr_syscall(syscall) \
struct augmented_enter_##syscall##_args { \
struct syscall_enter_##syscall##_args args; \
struct sockaddr_storage addr; \
}; \
int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
{ \
struct augmented_enter_##syscall##_args augmented_args; \
unsigned long addrlen = sizeof(augmented_args.addr); \
probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */ \
/* if (addrlen > augmented_args.args.addrlen) */ \
/* addrlen = augmented_args.args.addrlen; */ \
/* */ \
probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
&augmented_args, \
sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \
return 0; \
} \
int syscall_exit(syscall)(struct syscall_exit_args *args) \
{ \
return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
}
struct sockaddr;
struct syscall_enter_bind_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
struct sockaddr *addr_ptr;
unsigned long addrlen;
};
augmented_sockaddr_syscall(bind);
struct syscall_enter_connect_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
struct sockaddr *addr_ptr;
unsigned long addrlen;
};
augmented_sockaddr_syscall(connect);
struct syscall_enter_sendto_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
void *buff;
long len;
unsigned long flags;
struct sockaddr *addr_ptr;
long addr_len;
};
augmented_sockaddr_syscall(sendto);
license(GPL);

80
tools/perf/examples/bpf/etcsnoop.c Normal file
View File

@ -0,0 +1,80 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Augment the filename syscalls with the contents of the filename pointer argument
* filtering only those that do not start with /etc/.
*
* Test it with:
*
* perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
*
* It'll catch some openat syscalls related to the dynamic linked and
* the last one should be the one for '/etc/passwd'.
*
* This matches what is marshalled into the raw_syscall:sys_enter payload
* expected by the 'perf trace' beautifiers, and can be used by them unmodified,
* which will be done as that feature is implemented in the next csets, for now
* it will appear in a dump done by the default tracepoint handler in 'perf trace',
* that uses bpf_output__fprintf() to just dump those contents, as done with
* the bpf-output event associated with the __bpf_output__ map declared in
* tools/perf/include/bpf/stdio.h.
*/
#include <stdio.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
struct augmented_filename {
int size;
int reserved;
char value[64];
};
#define augmented_filename_syscall_enter(syscall) \
struct augmented_enter_##syscall##_args { \
struct syscall_enter_##syscall##_args args; \
struct augmented_filename filename; \
}; \
int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
{ \
char etc[6] = "/etc/"; \
struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \
probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \
sizeof(augmented_args.filename.value), \
args->filename_ptr); \
if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0) \
return 0; \
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
&augmented_args, \
(sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \
augmented_args.filename.size)); \
return 0; \
}
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
long dfd;
char *filename_ptr;
long flags;
long mode;
};
augmented_filename_syscall_enter(openat);
struct syscall_enter_open_args {
unsigned long long common_tp_fields;
long syscall_nr;
char *filename_ptr;
long flags;
long mode;
};
augmented_filename_syscall_enter(open);
license(GPL);

3
tools/perf/include/bpf/bpf.h
View File

@ -26,6 +26,9 @@ struct bpf_map {
#define syscall_enter(name) \
SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
#define syscall_exit(name) \
SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
#define license(name) \
char _license[] SEC("license") = #name; \
int _version SEC("version") = LINUX_VERSION_CODE;

24
tools/perf/include/bpf/linux/socket.h Normal file
View File

@ -0,0 +1,24 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_SOCKET_H
#define _UAPI_LINUX_SOCKET_H
/*
* Desired design of maximum size and alignment (see RFC2553)
*/
#define _K_SS_MAXSIZE 128 /* Implementation specific max size */
#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *))
/* Implementation specific desired alignment */
typedef unsigned short __kernel_sa_family_t;
struct __kernel_sockaddr_storage {
__kernel_sa_family_t ss_family; /* address family */
/* Following field(s) are implementation specific */
char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
/* space to achieve desired size, */
/* _SS_MAXSIZE value minus size of ss_family */
} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */
#define sockaddr_storage __kernel_sockaddr_storage
#endif /* _UAPI_LINUX_SOCKET_H */

2
tools/perf/tests/shell/record+probe_libc_inet_pton.sh
View File

@ -48,7 +48,7 @@ trace_libc_inet_pton_backtrace() {
*)
eventattr='max-stack=3'
echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
;;
esac

1
tools/perf/trace/beauty/Build
View File

@ -7,5 +7,6 @@ endif
libperf-y += kcmp.o
libperf-y += pkey_alloc.o
libperf-y += prctl.o
libperf-y += sockaddr.o
libperf-y += socket.o
libperf-y += statx.o

34
tools/perf/trace/beauty/beauty.h
View File

@ -30,9 +30,36 @@ struct thread;
size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
extern struct strarray strarray__socket_families;
/**
* augmented_arg: extra payload for syscall pointer arguments
* If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
* then its the arguments contents, so that we can show more than just a
* pointer. This will be done initially with eBPF, the start of that is at the
* tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
* will eventually be done automagically caching the running kernel tracefs
* events data into an eBPF C script, that then gets compiled and its .o file
* cached for subsequent use. For char pointers like the ones for 'open' like
* syscalls its easy, for the rest we should use DWARF or better, BTF, much
* more compact.
*
* @size: 8 if all we need is an integer, otherwise all of the augmented arg.
* @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
* @value: u64 aligned, for structs, pathnames
*/
struct augmented_arg {
int size;
int int_arg;
u64 value[];
};
/**
* @val: value of syscall argument being formatted
* @args: All the args, use syscall_args__val(arg, nth) to access one
* @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
* @augmented_args_size: augmented_args total payload size
* @thread: tid state (maps, pid, tid, etc)
* @trace: 'perf trace' internals: all threads, etc
* @parm: private area, may be an strarray, for instance
@ -43,6 +70,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
struct syscall_arg {
unsigned long val;
unsigned char *args;
struct {
struct augmented_arg *args;
int size;
} augmented;
struct thread *thread;
struct trace *trace;
void *parm;
@ -106,6 +137,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr
size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol

76
tools/perf/trace/beauty/sockaddr.c Normal file
View File

@ -0,0 +1,76 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
#include "trace/beauty/beauty.h"
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/un.h>
#include <arpa/inet.h>
static const char *socket_families[] = {
"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
"ALG", "NFC", "VSOCK",
};
DEFINE_STRARRAY(socket_families);
static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
{
struct sockaddr_in *sin = (struct sockaddr_in *)sa;
char tmp[16];
return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port),
inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
}
static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size)
{
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
u32 flowinfo = ntohl(sin6->sin6_flowinfo);
char tmp[512];
size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
if (flowinfo != 0)
printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
if (sin6->sin6_scope_id != 0)
printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
return printed;
}
static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size)
{
struct sockaddr_un *sun = (struct sockaddr_un *)sa;
return scnprintf(bf, size, ", path: %s", sun->sun_path);
}
static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = {
[AF_LOCAL] = af_local__scnprintf,
[AF_INET] = af_inet__scnprintf,
[AF_INET6] = af_inet6__scnprintf,
};
static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
{
struct sockaddr *sa = (struct sockaddr *)arg->augmented.args;
char family[32];
size_t printed;
strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family);
printed = scnprintf(bf, size, "{ .family: %s", family);
if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family])
printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed);
return printed + scnprintf(bf + printed, size - printed, " }");
}
size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg)
{
if (arg->augmented.args)
return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
return scnprintf(bf, size, "%#x", arg->val);
}

1
tools/perf/util/Build
View File

@ -73,6 +73,7 @@ libperf-y += vdso.o
libperf-y += counts.o
libperf-y += stat.o
libperf-y += stat-shadow.o
libperf-y += stat-display.o
libperf-y += record.o
libperf-y += srcline.o
libperf-y += data.o

32
tools/perf/util/annotate.c
View File

@ -246,8 +246,14 @@ find_target:
indirect_call:
tok = strchr(endptr, '*');
if (tok != NULL)
ops->target.addr = strtoull(tok + 1, NULL, 16);
if (tok != NULL) {
endptr++;
/* Indirect call can use a non-rip register and offset: callq *0x8(%rbx).
* Do not parse such instruction. */
if (strstr(endptr, "(%r") == NULL)
ops->target.addr = strtoull(endptr, NULL, 16);
}
goto find_target;
}
@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins)
return ins->ops == &call_ops || ins->ops == &s390_call_ops;
}
static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms)
/*
* Prevents from matching commas in the comment section, e.g.:
* ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast
*/
static inline const char *validate_comma(const char *c, struct ins_operands *ops)
{
if (ops->raw_comment && c > ops->raw_comment)
return NULL;
return c;
}
static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
{
struct map *map = ms->map;
struct symbol *sym = ms->sym;
@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
};
const char *c = strchr(ops->raw, ',');
u64 start, end;
ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
c = validate_comma(c, ops);
/*
* Examples of lines to parse for the _cpp_lex_token@@Base
* function:
@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
ops->target.addr = strtoull(c, NULL, 16);
if (!ops->target.addr) {
c = strchr(c, ',');
c = validate_comma(c, ops);
if (c++ != NULL)
ops->target.addr = strtoull(c, NULL, 16);
}
@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
c = strchr(ops->raw, ',');
c = validate_comma(c, ops);
if (c != NULL) {
const char *c2 = strchr(c + 1, ',');
c2 = validate_comma(c2, ops);
/* check for 3-op insn */
if (c2 != NULL)
c = c2;

1
tools/perf/util/annotate.h
View File

@ -22,6 +22,7 @@ struct ins {
struct ins_operands {
char *raw;
char *raw_comment;
struct {
char *raw;
char *name;

34
tools/perf/util/evsel.c
View File

@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
{
struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
if (evsel != NULL)
perf_evsel__init(evsel, attr, idx);
if (!evsel)
return NULL;
perf_evsel__init(evsel, attr, idx);
if (perf_evsel__is_bpf_output(evsel)) {
evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
@ -2939,3 +2940,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
return evsel->evlist->env;
return NULL;
}
static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
{
int cpu, thread;
for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd);
thread++) {
int fd = FD(evsel, cpu, thread);
if (perf_evlist__id_add_fd(evlist, evsel,
cpu, thread, fd) < 0)
return -1;
}
}
return 0;
}
int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
{
struct cpu_map *cpus = evsel->cpus;
struct thread_map *threads = evsel->threads;
if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
return -ENOMEM;
return store_evsel_ids(evsel, evlist);
}

1
tools/perf/util/evsel.h
View File

@ -481,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
#endif /* __PERF_EVSEL_H */

6
tools/perf/util/header.c
View File

@ -3637,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
}
int perf_event__synthesize_attrs(struct perf_tool *tool,
struct perf_session *session,
perf_event__handler_t process)
struct perf_evlist *evlist,
perf_event__handler_t process)
{
struct perf_evsel *evsel;
int err = 0;
evlist__for_each_entry(session->evlist, evsel) {
evlist__for_each_entry(evlist, evsel) {
err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
evsel->id, process);
if (err) {

2
tools/perf/util/header.h
View File

@ -124,7 +124,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
struct perf_event_attr *attr, u32 ids, u64 *id,
perf_event__handler_t process);
int perf_event__synthesize_attrs(struct perf_tool *tool,
struct perf_session *session,
struct perf_evlist *evlist,
perf_event__handler_t process);
int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
struct perf_evsel *evsel,

2
tools/perf/util/llvm-utils.c
View File

@ -19,7 +19,7 @@
#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \
"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"

15
tools/perf/util/map.c
View File

@ -320,12 +320,11 @@ int map__load(struct map *map)
build_id__sprintf(map->dso->build_id,
sizeof(map->dso->build_id),
sbuild_id);
pr_warning("%s with build id %s not found",
name, sbuild_id);
pr_debug("%s with build id %s not found", name, sbuild_id);
} else
pr_warning("Failed to open %s", name);
pr_debug("Failed to open %s", name);
pr_warning(", continuing without symbols\n");
pr_debug(", continuing without symbols\n");
return -1;
} else if (nr == 0) {
#ifdef HAVE_LIBELF_SUPPORT
@ -334,12 +333,11 @@ int map__load(struct map *map)
if (len > sizeof(DSO__DELETED) &&
strcmp(name + real_len + 1, DSO__DELETED) == 0) {
pr_warning("%.*s was updated (is prelink enabled?). "
pr_debug("%.*s was updated (is prelink enabled?). "
"Restart the long running apps that use it!\n",
(int)real_len, name);
} else {
pr_warning("no symbols found in %s, maybe install "
"a debug package?\n", name);
pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
}
#endif
return -1;
@ -701,8 +699,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
if (verbose >= 2) {
if (use_browser) {
pr_warning("overlapping maps in %s "
"(disable tui for more info)\n",
pr_debug("overlapping maps in %s (disable tui for more info)\n",
map->dso->name);
} else {
fputs("overlapping maps:\n", fp);

94
tools/perf/util/s390-cpumsf.c
View File

@ -147,6 +147,9 @@
#include <linux/bitops.h>
#include <linux/log2.h>
#include <sys/stat.h>
#include <sys/types.h>
#include "cpumap.h"
#include "color.h"
#include "evsel.h"
@ -159,6 +162,7 @@
#include "auxtrace.h"
#include "s390-cpumsf.h"
#include "s390-cpumsf-kernel.h"
#include "config.h"
struct s390_cpumsf {
struct auxtrace auxtrace;
@ -170,6 +174,8 @@ struct s390_cpumsf {
u32 pmu_type;
u16 machine_type;
bool data_queued;
bool use_logfile;
char *logdir;
};
struct s390_cpumsf_queue {
@ -177,6 +183,7 @@ struct s390_cpumsf_queue {
unsigned int queue_nr;
struct auxtrace_buffer *buffer;
int cpu;
FILE *logfile;
};
/* Display s390 CPU measurement facility basic-sampling data entry */
@ -595,6 +602,12 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
buffer->use_size = buffer->size;
buffer->use_data = buffer->data;
}
if (sfq->logfile) { /* Write into log file */
size_t rc = fwrite(buffer->data, buffer->size, 1,
sfq->logfile);
if (rc != 1)
pr_err("Failed to write auxiliary data\n");
}
} else
buffer = sfq->buffer;
@ -606,6 +619,13 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
return -ENOMEM;
buffer->use_size = buffer->size;
buffer->use_data = buffer->data;
if (sfq->logfile) { /* Write into log file */
size_t rc = fwrite(buffer->data, buffer->size, 1,
sfq->logfile);
if (rc != 1)
pr_err("Failed to write auxiliary data\n");
}
}
pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
__func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@ -640,6 +660,23 @@ s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
sfq->sf = sf;
sfq->queue_nr = queue_nr;
sfq->cpu = -1;
if (sf->use_logfile) {
char *name;
int rc;
rc = (sf->logdir)
? asprintf(&name, "%s/aux.smp.%02x",
sf->logdir, queue_nr)
: asprintf(&name, "aux.smp.%02x", queue_nr);
if (rc > 0)
sfq->logfile = fopen(name, "w");
if (sfq->logfile == NULL) {
pr_err("Failed to open auxiliary log file %s,"
"continue...\n", name);
sf->use_logfile = false;
}
free(name);
}
return sfq;
}
@ -850,8 +887,16 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
struct auxtrace_queues *queues = &sf->queues;
unsigned int i;
for (i = 0; i < queues->nr_queues; i++)
for (i = 0; i < queues->nr_queues; i++) {
struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
queues->queue_array[i].priv;
if (sfq != NULL && sfq->logfile) {
fclose(sfq->logfile);
sfq->logfile = NULL;
}
zfree(&queues->queue_array[i].priv);
}
auxtrace_queues__free(queues);
}
@ -864,6 +909,7 @@ static void s390_cpumsf_free(struct perf_session *session)
auxtrace_heap__free(&sf->heap);
s390_cpumsf_free_queues(session);
session->auxtrace = NULL;
free(sf->logdir);
free(sf);
}
@ -877,17 +923,55 @@ static int s390_cpumsf_get_type(const char *cpuid)
/* Check itrace options set on perf report command.
* Return true, if none are set or all options specified can be
* handled on s390.
* handled on s390 (currently only option 'd' for logging.
* Return false otherwise.
*/
static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
{
bool ison = false;
if (!itops || !itops->set)
return true;
pr_err("No --itrace options supported\n");
ison = itops->inject || itops->instructions || itops->branches ||
itops->transactions || itops->ptwrites ||
itops->pwr_events || itops->errors ||
itops->dont_decode || itops->calls || itops->returns ||
itops->callchain || itops->thread_stack ||
itops->last_branch;
if (!ison)
return true;
pr_err("Unsupported --itrace options specified\n");
return false;
}
/* Check for AUXTRACE dump directory if it is needed.
* On failure print an error message but continue.
* Return 0 on wrong keyword in config file and 1 otherwise.
*/
static int s390_cpumsf__config(const char *var, const char *value, void *cb)
{
struct s390_cpumsf *sf = cb;
struct stat stbuf;
int rc;
if (strcmp(var, "auxtrace.dumpdir"))
return 0;
sf->logdir = strdup(value);
if (sf->logdir == NULL) {
pr_err("Failed to find auxtrace log directory %s,"
" continue with current directory...\n", value);
return 1;
}
rc = stat(sf->logdir, &stbuf);
if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
pr_err("Missing auxtrace log directory %s,"
" continue with current directory...\n", value);
free(sf->logdir);
sf->logdir = NULL;
}
return 1;
}
int s390_cpumsf_process_auxtrace_info(union perf_event *event,
struct perf_session *session)
{
@ -906,6 +990,9 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
err = -EINVAL;
goto err_free;
}
sf->use_logfile = session->itrace_synth_opts->log;
if (sf->use_logfile)
perf_config(s390_cpumsf__config, sf);
err = auxtrace_queues__init(&sf->queues);
if (err)
@ -940,6 +1027,7 @@ err_free_queues:
auxtrace_queues__free(&sf->queues);
session->auxtrace = NULL;
err_free:
free(sf->logdir);
free(sf);
return err;
}

1166
tools/perf/util/stat-display.c Normal file
View File

File diff suppressed because it is too large Load Diff

147
tools/perf/util/stat-shadow.c
View File

@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st,
return v->stats.n;
}
static void print_stalled_cycles_frontend(int cpu,
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu,
color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
if (ratio)
out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
ratio);
else
out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
static void print_stalled_cycles_backend(int cpu,
static void print_stalled_cycles_backend(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu,
color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
}
static void print_branch_misses(int cpu,
static void print_branch_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -469,10 +472,11 @@ static void print_branch_misses(int cpu,
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
}
static void print_l1_dcache_misses(int cpu,
static void print_l1_dcache_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu,
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
}
static void print_l1_icache_misses(int cpu,
static void print_l1_icache_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
}
static void print_dtlb_cache_misses(int cpu,
static void print_dtlb_cache_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
}
static void print_itlb_cache_misses(int cpu,
static void print_itlb_cache_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
}
static void print_ll_cache_misses(int cpu,
static void print_ll_cache_misses(struct perf_stat_config *config,
int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
}
/*
@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
return sanitize_val(1.0 - sum);
}
static void print_smi_cost(int cpu, struct perf_evsel *evsel,
static void print_smi_cost(struct perf_stat_config *config,
int cpu, struct perf_evsel *evsel,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
{
@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
if (cost > 10)
color = PERF_COLOR_RED;
out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
}
static void generic_metric(const char *metric_expr,
static void generic_metric(struct perf_stat_config *config,
const char *metric_expr,
struct perf_evsel **metric_events,
char *name,
const char *metric_name,
@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr,
const char *p = metric_expr;
if (expr__parse(&ratio, &pctx, &p) == 0)
print_metric(ctxp, NULL, "%8.1f",
print_metric(config, ctxp, NULL, "%8.1f",
metric_name ?
metric_name :
out->force_header ? name : "",
ratio);
else
print_metric(ctxp, NULL, NULL,
print_metric(config, ctxp, NULL, NULL,
out->force_header ?
(metric_name ? metric_name : name) : "", 0);
} else
print_metric(ctxp, NULL, NULL, "", 0);
print_metric(config, ctxp, NULL, NULL, "", 0);
}
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
if (total) {
ratio = avg / total;
print_metric(ctxp, NULL, "%7.2f ",
print_metric(config, ctxp, NULL, "%7.2f ",
"insn per cycle", ratio);
} else {
print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
ctx, cpu));
if (total && avg) {
out->new_line(ctxp);
out->new_line(config, ctxp);
ratio = total / avg;
print_metric(ctxp, NULL, "%7.2f ",
print_metric(config, ctxp, NULL, "%7.2f ",
"stalled cycles per insn",
ratio);
} else if (have_frontend_stalled) {
print_metric(ctxp, NULL, NULL,
print_metric(config, ctxp, NULL, NULL,
"stalled cycles per insn", 0);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
print_branch_misses(cpu, evsel, avg, out, st);
print_branch_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all branches", 0);
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
print_l1_dcache_misses(cpu, evsel, avg, out, st);
print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
print_l1_icache_misses(cpu, evsel, avg, out, st);
print_l1_icache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
print_dtlb_cache_misses(cpu, evsel, avg, out, st);
print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
print_itlb_cache_misses(cpu, evsel, avg, out, st);
print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
print_ll_cache_misses(cpu, evsel, avg, out, st);
print_ll_cache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
ratio = avg * 100 / total;
if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
print_metric(ctxp, NULL, "%8.3f %%",
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
print_stalled_cycles_backend(cpu, evsel, avg, out, st);
print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
if (total) {
ratio = avg / total;
print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
} else {
print_metric(ctxp, NULL, NULL, "Ghz", 0);
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
if (total)
print_metric(ctxp, NULL,
print_metric(config, ctxp, NULL,
"%7.2f%%", "transactional cycles",
100.0 * (avg / total));
else
print_metric(ctxp, NULL, NULL, "transactional cycles",
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
if (total2 < avg)
total2 = avg;
if (total)
print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
100.0 * ((total2-avg) / total));
else
print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
ctx, cpu);
@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
ratio = total / avg;
if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
print_metric(ctxp, NULL, "%8.0f",
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(ctxp, NULL, NULL, "cycles / transaction",
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@ -912,33 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
if (avg)
ratio = total / avg;
print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
} else if (perf_evsel__is_clock(evsel)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
avg / (ratio * evsel->scale));
else
print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
double fe_bound = td_fe_bound(ctx, cpu, st);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(ctxp, color, "%8.1f%%", "frontend bound",
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
double retiring = td_retiring(ctx, cpu, st);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(ctxp, color, "%8.1f%%", "retiring",
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
double bad_spec = td_bad_spec(ctx, cpu, st);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(ctxp, color, "%8.1f%%", "bad speculation",
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
double be_bound = td_be_bound(ctx, cpu, st);
@ -955,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
if (td_total_slots(ctx, cpu, st) > 0)
print_metric(ctxp, color, "%8.1f%%", name,
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(ctxp, NULL, NULL, name, 0);
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (evsel->metric_expr) {
generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
evsel->metric_name, avg, cpu, out, st);
} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
@ -975,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
unit = 'K';
}
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
print_smi_cost(cpu, evsel, out, st);
print_smi_cost(config, cpu, evsel, out, st);
} else {
num = 0;
}
@ -987,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
list_for_each_entry (mexp, &me->head, nd) {
if (num++ > 0)
out->new_line(ctxp);
generic_metric(mexp->metric_expr, mexp->metric_events,
out->new_line(config, ctxp);
generic_metric(config, mexp->metric_expr, mexp->metric_events,
evsel->name, mexp->metric_name,
avg, cpu, out, st);
}
}
if (num == 0)
print_metric(ctxp, NULL, NULL, NULL, 0);
print_metric(config, ctxp, NULL, NULL, NULL, 0);
}

95
tools/perf/util/stat.c
View File

@ -435,3 +435,98 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
return ret;
}
int create_perf_stat_counter(struct perf_evsel *evsel,
struct perf_stat_config *config,
struct target *target)
{
struct perf_event_attr *attr = &evsel->attr;
struct perf_evsel *leader = evsel->leader;
if (config->scale) {
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
}
/*
* The event is part of non trivial group, let's enable
* the group read (for leader) and ID retrieval for all
* members.
*/
if (leader->nr_members > 1)
attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
attr->inherit = !config->no_inherit;
/*
* Some events get initialized with sample_(period/type) set,
* like tracepoints. Clear it up for counting.
*/
attr->sample_period = 0;
if (config->identifier)
attr->sample_type = PERF_SAMPLE_IDENTIFIER;
/*
* Disabling all counters initially, they will be enabled
* either manually by us or by kernel via enable_on_exec
* set later.
*/
if (perf_evsel__is_group_leader(evsel)) {
attr->disabled = 1;
/*
* In case of initial_delay we enable tracee
* events manually.
*/
if (target__none(target) && !config->initial_delay)
attr->enable_on_exec = 1;
}
if (target__has_cpu(target) && !target__has_per_thread(target))
return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
return perf_evsel__open_per_thread(evsel, evsel->threads);
}
int perf_stat_synthesize_config(struct perf_stat_config *config,
struct perf_tool *tool,
struct perf_evlist *evlist,
perf_event__handler_t process,
bool attrs)
{
int err;
if (attrs) {
err = perf_event__synthesize_attrs(tool, evlist, process);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
return err;
}
}
err = perf_event__synthesize_extra_attr(tool, evlist, process,
attrs);
err = perf_event__synthesize_thread_map2(tool, evlist->threads,
process, NULL);
if (err < 0) {
pr_err("Couldn't synthesize thread map.\n");
return err;
}
err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
process, NULL);
if (err < 0) {
pr_err("Couldn't synthesize thread map.\n");
return err;
}
err = perf_event__synthesize_stat_config(tool, config, process, NULL);
if (err < 0) {
pr_err("Couldn't synthesize config.\n");
return err;
}
return 0;
}

72
tools/perf/util/stat.h
View File

@ -4,8 +4,14 @@
#include <linux/types.h>
#include <stdio.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/wait.h>
#include "xyarray.h"
#include "rblist.h"
#include "perf.h"
#include "event.h"
struct stats {
double n, mean, M2;
@ -84,15 +90,42 @@ struct runtime_stat {
struct rblist value_list;
};
typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
struct cpu_map *m, int cpu);
struct perf_stat_config {
enum aggr_mode aggr_mode;
bool scale;
FILE *output;
unsigned int interval;
unsigned int timeout;
int times;
struct runtime_stat *stats;
int stats_num;
enum aggr_mode aggr_mode;
bool scale;
bool no_inherit;
bool identifier;
bool csv_output;
bool interval_clear;
bool metric_only;
bool null_run;
bool ru_display;
bool big_num;
bool no_merge;
bool walltime_run_table;
FILE *output;
unsigned int interval;
unsigned int timeout;
unsigned int initial_delay;
unsigned int unit_width;
unsigned int metric_only_len;
int times;
int run_count;
int print_free_counters_hint;
int print_mixed_hw_group_error;
struct runtime_stat *stats;
int stats_num;
const char *csv_sep;
struct stats *walltime_nsecs_stats;
struct rusage ru_data;
struct cpu_map *aggr_map;
aggr_get_id_t aggr_get_id;
struct cpu_map *cpus_aggr_map;
u64 *walltime_run;
struct rblist metric_events;
};
void update_stats(struct stats *stats, u64 val);
@ -130,9 +163,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
extern struct runtime_stat rt_stat;
extern struct stats walltime_nsecs_stats;
typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
typedef void (*print_metric_t)(struct perf_stat_config *config,
void *ctx, const char *color, const char *unit,
const char *fmt, double val);
typedef void (*new_line_t )(void *ctx);
typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
void runtime_stat__init(struct runtime_stat *st);
void runtime_stat__exit(struct runtime_stat *st);
@ -148,7 +182,8 @@ struct perf_stat_output_ctx {
bool force_header;
};
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
@ -171,4 +206,19 @@ int perf_event__process_stat_event(struct perf_tool *tool,
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
int create_perf_stat_counter(struct perf_evsel *evsel,
struct perf_stat_config *config,
struct target *target);
int perf_stat_synthesize_config(struct perf_stat_config *config,
struct perf_tool *tool,
struct perf_evlist *evlist,
perf_event__handler_t process,
bool attrs);
void
perf_evlist__print_counters(struct perf_evlist *evlist,
struct perf_stat_config *config,
struct target *_target,
struct timespec *ts,
int argc, const char **argv);
#endif

2
tools/perf/util/trace-event-info.c
View File

@ -377,7 +377,7 @@ out:
static int record_saved_cmdline(void)
{
unsigned int size;
unsigned long long size;
char *path;
struct stat st;
int ret, err = 0;

7
tools/perf/util/trace-event-parse.c
View File

@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent,
void parse_saved_cmdline(struct tep_handle *pevent,
char *file, unsigned int size __maybe_unused)
{
char *comm;
char comm[17]; /* Max comm length in the kernel is 16. */
char *line;
char *next = NULL;
int pid;
line = strtok_r(file, "\n", &next);
while (line) {
sscanf(line, "%d %ms", &pid, &comm);
tep_register_comm(pevent, comm, pid);
free(comm);
if (sscanf(line, "%d %16s", &pid, comm) == 2)
tep_register_comm(pevent, comm, pid);
line = strtok_r(NULL, "\n", &next);
}
}

1
tools/perf/util/trace-event.h
View File

@ -3,6 +3,7 @@
#define _PERF_UTIL_TRACE_EVENT_H
#include <traceevent/event-parse.h>
#include <traceevent/trace-seq.h>
#include "parse-events.h"
struct machine;