linux-stable/tools/perf/util/branch.c
Sandipan Das 6ade6c6460 perf script: Show branch speculation info
Show the branch speculation info if provided by the branch recording
hardware feature. This can be useful for optimizing code further.

The speculation info is appended to the end of the list of fields so any
existing tools that use "/" as a delimiter for access fields via an index
remain unaffected. Also show "-" instead of "N/A" when speculation info
is unavailable because "/" is used as the field separator.

E.g.

  $ perf record -j any,u,save_type ./test_branch
  $ perf script --fields brstacksym

Before:

  [...]
  check_match+0x60/strcmp+0x0/P/-/-/0/CALL
  do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL
  [...]

After:

  [...]
  check_match+0x60/strcmp+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH
  do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH
  [...]

The bitfield swapping scheme used duing sample parsing has changed
because of the addition of new branch flags, namely "spec", "new_type"
and "priv". Earlier, these were all part of the "reserved" field but
now, each of these fields get swapped separately. Change the expected
flag values accordingly for the test to pass.

E.g.

  $ perf test -v 27

Before:

   27: Sample parsing                                                  :
  --- start ---
  test child forked, pid 61979
  parsing failed for sample_type 0x800
  test child finished with -1
  ---- end ----
  Sample parsing: FAILED!

After:

   27: Sample parsing                                                  :
  --- start ---
  test child forked, pid 63293
  test child finished with 0
  ---- end ----
  Sample parsing: Ok

Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: x86@kernel.org
Link: https://lore.kernel.org/r/56e272583552526e999ba0b536ac009ae3613966.1675333809.git.sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-02 17:18:31 -03:00

229 lines
4.7 KiB
C

#include "util/map_symbol.h"
#include "util/branch.h"
#include <linux/kernel.h>
static bool cross_area(u64 addr1, u64 addr2, int size)
{
u64 align1, align2;
align1 = addr1 & ~(size - 1);
align2 = addr2 & ~(size - 1);
return (align1 != align2) ? true : false;
}
#define AREA_4K 4096
#define AREA_2M (2 * 1024 * 1024)
void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
u64 from, u64 to)
{
if (flags->type == PERF_BR_UNKNOWN || from == 0)
return;
if (flags->type == PERF_BR_EXTEND_ABI)
st->new_counts[flags->new_type]++;
else
st->counts[flags->type]++;
if (flags->type == PERF_BR_COND) {
if (to > from)
st->cond_fwd++;
else
st->cond_bwd++;
}
if (cross_area(from, to, AREA_2M))
st->cross_2m++;
else if (cross_area(from, to, AREA_4K))
st->cross_4k++;
}
const char *branch_new_type_name(int new_type)
{
const char *branch_new_names[PERF_BR_NEW_MAX] = {
"FAULT_ALGN",
"FAULT_DATA",
"FAULT_INST",
/*
* TODO: This switch should happen on 'session->header.env.arch'
* instead, because an arm64 platform perf recording could be
* opened for analysis on other platforms as well.
*/
#ifdef __aarch64__
"ARM64_FIQ",
"ARM64_DEBUG_HALT",
"ARM64_DEBUG_EXIT",
"ARM64_DEBUG_INST",
"ARM64_DEBUG_DATA"
#else
"ARCH_1",
"ARCH_2",
"ARCH_3",
"ARCH_4",
"ARCH_5"
#endif
};
if (new_type >= 0 && new_type < PERF_BR_NEW_MAX)
return branch_new_names[new_type];
return NULL;
}
const char *branch_type_name(int type)
{
const char *branch_names[PERF_BR_MAX] = {
"N/A",
"COND",
"UNCOND",
"IND",
"CALL",
"IND_CALL",
"RET",
"SYSCALL",
"SYSRET",
"COND_CALL",
"COND_RET",
"ERET",
"IRQ",
"SERROR",
"NO_TX",
"", // Needed for PERF_BR_EXTEND_ABI that ends up triggering some compiler warnings about NULL deref
};
if (type >= 0 && type < PERF_BR_MAX)
return branch_names[type];
return NULL;
}
const char *get_branch_type(struct branch_entry *e)
{
if (e->flags.type == PERF_BR_UNKNOWN)
return "";
if (e->flags.type == PERF_BR_EXTEND_ABI)
return branch_new_type_name(e->flags.new_type);
return branch_type_name(e->flags.type);
}
void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
{
u64 total = 0;
int i;
for (i = 0; i < PERF_BR_MAX; i++)
total += st->counts[i];
if (total == 0)
return;
fprintf(fp, "\n#");
fprintf(fp, "\n# Branch Statistics:");
fprintf(fp, "\n#");
if (st->cond_fwd > 0) {
fprintf(fp, "\n%8s: %5.1f%%",
"COND_FWD",
100.0 * (double)st->cond_fwd / (double)total);
}
if (st->cond_bwd > 0) {
fprintf(fp, "\n%8s: %5.1f%%",
"COND_BWD",
100.0 * (double)st->cond_bwd / (double)total);
}
if (st->cross_4k > 0) {
fprintf(fp, "\n%8s: %5.1f%%",
"CROSS_4K",
100.0 * (double)st->cross_4k / (double)total);
}
if (st->cross_2m > 0) {
fprintf(fp, "\n%8s: %5.1f%%",
"CROSS_2M",
100.0 * (double)st->cross_2m / (double)total);
}
for (i = 0; i < PERF_BR_MAX; i++) {
if (st->counts[i] > 0)
fprintf(fp, "\n%8s: %5.1f%%",
branch_type_name(i),
100.0 *
(double)st->counts[i] / (double)total);
}
for (i = 0; i < PERF_BR_NEW_MAX; i++) {
if (st->new_counts[i] > 0)
fprintf(fp, "\n%8s: %5.1f%%",
branch_new_type_name(i),
100.0 *
(double)st->new_counts[i] / (double)total);
}
}
static int count_str_scnprintf(int idx, const char *str, char *bf, int size)
{
return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str);
}
int branch_type_str(struct branch_type_stat *st, char *bf, int size)
{
int i, j = 0, printed = 0;
u64 total = 0;
for (i = 0; i < PERF_BR_MAX; i++)
total += st->counts[i];
for (i = 0; i < PERF_BR_NEW_MAX; i++)
total += st->new_counts[i];
if (total == 0)
return 0;
if (st->cond_fwd > 0)
printed += count_str_scnprintf(j++, "COND_FWD", bf + printed, size - printed);
if (st->cond_bwd > 0)
printed += count_str_scnprintf(j++, "COND_BWD", bf + printed, size - printed);
for (i = 0; i < PERF_BR_MAX; i++) {
if (i == PERF_BR_COND)
continue;
if (st->counts[i] > 0)
printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed);
}
for (i = 0; i < PERF_BR_NEW_MAX; i++) {
if (st->new_counts[i] > 0)
printed += count_str_scnprintf(j++, branch_new_type_name(i), bf + printed, size - printed);
}
if (st->cross_4k > 0)
printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed);
if (st->cross_2m > 0)
printed += count_str_scnprintf(j++, "CROSS_2M", bf + printed, size - printed);
return printed;
}
const char *branch_spec_desc(int spec)
{
const char *branch_spec_outcomes[PERF_BR_SPEC_MAX] = {
"N/A",
"SPEC_WRONG_PATH",
"NON_SPEC_CORRECT_PATH",
"SPEC_CORRECT_PATH",
};
if (spec >= 0 && spec < PERF_BR_SPEC_MAX)
return branch_spec_outcomes[spec];
return NULL;
}