From: kan.liang@linux.intel.com
To: acme@kernel.org, namhyung@kernel.org, irogers@google.com,
peterz@infradead.org, mingo@kernel.org,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Cc: adrian.hunter@intel.com, ak@linux.intel.com, eranian@google.com,
Kan Liang <kan.liang@linux.intel.com>,
Tinghao Zhang <tinghao.zhang@intel.com>
Subject: [PATCH V2 8/9] perf script: Add branch counters
Date: Thu, 8 Aug 2024 12:33:23 -0700 [thread overview]
Message-ID: <20240808193324.2027665-9-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20240808193324.2027665-1-kan.liang@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
It's useful to print the branch counter information for each jump in
the brstackinsn when it's available.
Add a new field brcntr to display the branch counter information.
By default, the abbreviation will be used to indicate the branch
counter. In the verbose mode, the real event name is shown.
$perf script -F +brstackinsn,+brcntr
# Branch counter abbr list:
# branch-instructions:ppp = A
# branch-misses = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
tchain_edit 332203 3366329.405674: 53030 branch-instructions:ppp: 401781 f3+0x2c (home/sdp/test/tchain_edit)
f3+31:
0000000000401774 insn: eb 04 br_cntr: AA # PRED 5 cycles [5]
000000000040177a insn: 81 7d fc 0f 27 00 00
0000000000401781 insn: 7e e3 br_cntr: A # PRED 1 cycles [6] 2.00 IPC
0000000000401766 insn: 8b 45 fc
0000000000401769 insn: 83 e0 01
000000000040176c insn: 85 c0
000000000040176e insn: 74 06 br_cntr: A # PRED 1 cycles [7] 4.00 IPC
0000000000401776 insn: 83 45 fc 01
000000000040177a insn: 81 7d fc 0f 27 00 00
0000000000401781 insn: 7e e3 br_cntr: A # PRED 7 cycles [14] 0.43 IPC
$perf script -F +brstackinsn,+brcntr -v
tchain_edit 332203 3366329.405674: 53030 branch-instructions:ppp: 401781 f3+0x2c (/home/sdp/os.linux.perf.test-suite/kernels/lbr_kernel/tchain_edit)
f3+31:
0000000000401774 insn: eb 04 br_cntr: branch-instructions:ppp 2 branch-misses 0 # PRED 5 cycles [5]
000000000040177a insn: 81 7d fc 0f 27 00 00
0000000000401781 insn: 7e e3 br_cntr: branch-instructions:ppp 1 branch-misses 0 # PRED 1 cycles [6] 2.00 IPC
0000000000401766 insn: 8b 45 fc
0000000000401769 insn: 83 e0 01
000000000040176c insn: 85 c0
000000000040176e insn: 74 06 br_cntr: branch-instructions:ppp 1 branch-misses 0 # PRED 1 cycles [7] 4.00 IPC
0000000000401776 insn: 83 45 fc 01
000000000040177a insn: 81 7d fc 0f 27 00 00
0000000000401781 insn: 7e e3 br_cntr: branch-instructions:ppp 1 branch-misses 0 # PRED 7 cycles [14] 0.43 IPC
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
tools/perf/Documentation/perf-script.txt | 2 +-
tools/perf/builtin-script.c | 69 +++++++++++++++++++++---
2 files changed, 63 insertions(+), 8 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index ff086ef05a0c..be483c904d8d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -134,7 +134,7 @@ OPTIONS
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
brstackinsn, brstackinsnlen, brstackdisasm, brstackoff, callindent, insn, disasm,
insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size,
- code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat,
+ code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat, brcntr,
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c16224b1fef3..4d71847196bc 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -62,6 +62,7 @@
#include "util/record.h"
#include "util/util.h"
#include "util/cgroup.h"
+#include "util/annotate.h"
#include "perf.h"
#include <linux/ctype.h>
@@ -138,6 +139,7 @@ enum perf_output_field {
PERF_OUTPUT_DSOFF = 1ULL << 41,
PERF_OUTPUT_DISASM = 1ULL << 42,
PERF_OUTPUT_BRSTACKDISASM = 1ULL << 43,
+ PERF_OUTPUT_BRCNTR = 1ULL << 44,
};
struct perf_script {
@@ -213,6 +215,7 @@ struct output_option {
{.str = "cgroup", .field = PERF_OUTPUT_CGROUP},
{.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT},
{.str = "brstackdisasm", .field = PERF_OUTPUT_BRSTACKDISASM},
+ {.str = "brcntr", .field = PERF_OUTPUT_BRCNTR},
};
enum {
@@ -520,6 +523,12 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
"Hint: run 'perf record -b ...'\n");
return -EINVAL;
}
+ if (PRINT_FIELD(BRCNTR) &&
+ !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_COUNTERS)) {
+ pr_err("Display of branch counter requested but it's not enabled\n"
+ "Hint: run 'perf record -j any,counter ...'\n");
+ return -EINVAL;
+ }
if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID))
return -EINVAL;
@@ -789,6 +798,19 @@ static int perf_sample__fprintf_start(struct perf_script *script,
int printed = 0;
char tstr[128];
+ /*
+ * Print the branch counter's abbreviation list,
+ * if the branch counter is available.
+ */
+ if (PRINT_FIELD(BRCNTR) && !verbose) {
+ char *buf;
+
+ if (!annotation_br_cntr_abbr_list(&buf, evsel, true)) {
+ printed += fprintf(stdout, "%s", buf);
+ free(buf);
+ }
+ }
+
if (PRINT_FIELD(MACHINE_PID) && sample->machine_pid)
printed += fprintf(fp, "VM:%5d ", sample->machine_pid);
@@ -1195,7 +1217,9 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
struct perf_insn *x, u8 *inbuf, int len,
int insn, FILE *fp, int *total_cycles,
struct perf_event_attr *attr,
- struct thread *thread)
+ struct thread *thread,
+ struct evsel *evsel,
+ u64 br_cntr)
{
int ilen = 0;
int printed = fprintf(fp, "\t%016" PRIx64 "\t", ip);
@@ -1216,6 +1240,28 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
addr_location__exit(&al);
}
+ if (PRINT_FIELD(BRCNTR)) {
+ unsigned int width = evsel__env(evsel)->br_cntr_width;
+ unsigned int i = 0, j, num, mask = (1L << width) - 1;
+ struct evsel *pos = evsel__leader(evsel);
+
+ printed += fprintf(fp, "br_cntr: ");
+ evlist__for_each_entry_from(evsel->evlist, pos) {
+ if (!(pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+ continue;
+ if (evsel__leader(pos) != evsel__leader(evsel))
+ break;
+
+ num = (br_cntr >> (i++ * width)) & mask;
+ if (!verbose) {
+ for (j = 0; j < num; j++)
+ printed += fprintf(fp, "%s", pos->abbr_name);
+ } else
+ printed += fprintf(fp, "%s %d ", pos->name, num);
+ }
+ printed += fprintf(fp, "\t");
+ }
+
printed += fprintf(fp, "#%s%s%s%s",
en->flags.predicted ? " PRED" : "",
en->flags.mispred ? " MISPRED" : "",
@@ -1272,6 +1318,7 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
}
static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
+ struct evsel *evsel,
struct thread *thread,
struct perf_event_attr *attr,
struct machine *machine, FILE *fp)
@@ -1285,6 +1332,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
unsigned off;
struct symbol *lastsym = NULL;
int total_cycles = 0;
+ u64 br_cntr = 0;
if (!(br && br->nr))
return 0;
@@ -1296,6 +1344,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
x.machine = machine;
x.cpu = sample->cpu;
+ if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr)
+ br_cntr = sample->branch_stack_cntr[nr - 1];
+
printed += fprintf(fp, "%c", '\n');
/* Handle first from jump, of which we don't know the entry. */
@@ -1307,7 +1358,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
x.cpumode, x.cpu, &lastsym, attr, fp);
printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
&x, buffer, len, 0, fp, &total_cycles,
- attr, thread);
+ attr, thread, evsel, br_cntr);
if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
}
@@ -1337,8 +1388,10 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) {
+ if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr)
+ br_cntr = sample->branch_stack_cntr[i];
printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
- &total_cycles, attr, thread);
+ &total_cycles, attr, thread, evsel, br_cntr);
if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, ip);
break;
@@ -1547,6 +1600,7 @@ void script_fetch_insn(struct perf_sample *sample, struct thread *thread,
}
static int perf_sample__fprintf_insn(struct perf_sample *sample,
+ struct evsel *evsel,
struct perf_event_attr *attr,
struct thread *thread,
struct machine *machine, FILE *fp,
@@ -1567,7 +1621,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
printed += sample__fprintf_insn_asm(sample, thread, machine, fp, al);
}
if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM))
- printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
+ printed += perf_sample__fprintf_brstackinsn(sample, evsel, thread, attr, machine, fp);
return printed;
}
@@ -1639,7 +1693,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
if (print_srcline_last)
printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp);
- printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
+ printed += perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al);
printed += fprintf(fp, "\n");
if (PRINT_FIELD(SRCCODE)) {
int ret = map__fprintf_srccode(al->map, al->addr, stdout,
@@ -2297,7 +2351,7 @@ static void process_event(struct perf_script *script,
if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
perf_sample__fprintf_bpf_output(sample, fp);
- perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
+ perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al);
if (PRINT_FIELD(PHYS_ADDR))
fprintf(fp, "%16" PRIx64, sample->phys_addr);
@@ -3979,7 +4033,8 @@ int cmd_script(int argc, const char **argv)
"brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
"brstackinsnlen,brstackdisasm,brstackoff,callindent,insn,disasm,insnlen,synth,"
"phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
- "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
+ "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat,"
+ "brcntr",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
--
2.38.1
next prev parent reply other threads:[~2024-08-08 19:32 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-08 19:33 [PATCH V2 0/9] Support branch counters in block annotation kan.liang
2024-08-08 19:33 ` [PATCH V2 1/9] perf report: Fix --total-cycles --stdio output error kan.liang
2024-08-08 19:33 ` [PATCH V2 2/9] perf report: Remove the first overflow check for branch counters kan.liang
2024-08-08 19:33 ` [PATCH V2 3/9] perf evlist: Save branch counters information kan.liang
2024-08-08 19:33 ` [PATCH V2 4/9] perf annotate: Save branch counters for each block kan.liang
2024-08-08 19:33 ` [PATCH V2 5/9] perf evsel: Assign abbr name for the branch counter events kan.liang
2024-08-08 19:33 ` [PATCH V2 6/9] perf report: Display the branch counter histogram kan.liang
2024-08-08 19:33 ` [PATCH V2 7/9] perf annotate: " kan.liang
2024-08-08 19:33 ` kan.liang [this message]
2024-08-08 19:33 ` [PATCH V2 9/9] perf test: Add new test cases for the branch counter feature kan.liang
2024-08-08 20:27 ` [PATCH V2 0/9] Support branch counters in block annotation Andi Kleen
2024-08-12 19:39 ` Namhyung Kim
2024-08-12 20:13 ` Arnaldo Carvalho de Melo
2024-08-13 15:15 ` Liang, Kan
2024-08-13 15:17 ` Arnaldo Carvalho de Melo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240808193324.2027665-9-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=tinghao.zhang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox