From: Jin Yao <yao.jin@linux.intel.com>
To: acme@kernel.org, jolsa@kernel.org, peterz@infradead.org,
mingo@redhat.com, alexander.shishkin@linux.intel.com
Cc: Linux-kernel@vger.kernel.org, ak@linux.intel.com,
kan.liang@intel.com, yao.jin@intel.com,
linuxppc-dev@lists.ozlabs.org, Jin Yao <yao.jin@linux.intel.com>
Subject: [PATCH v2 4/5] perf report: Show branch type statistics for stdio mode
Date: Fri, 7 Apr 2017 18:47:45 +0800 [thread overview]
Message-ID: <1491562066-7472-5-git-send-email-yao.jin@linux.intel.com> (raw)
In-Reply-To: <1491562066-7472-1-git-send-email-yao.jin@linux.intel.com>
Show the branch type statistics at the end of perf report --stdio.
For example:
perf report --stdio
JCC forward: 27.7%
JCC backward: 9.8%
JMP: 0.0%
IND_JMP: 6.5%
CALL: 26.6%
IND_CALL: 0.0%
RET: 29.3%
IRET: 0.0%
CROSS_4K: 0.0%
CROSS_2M: 14.3%
The branch types are:
---------------------
JCC forward: Conditional forward jump
JCC backward: Conditional backward jump
JMP: Jump imm
IND_JMP: Jump reg/mem
CALL: Call imm
IND_CALL: Call reg/mem
RET: Ret
SYSCALL: Syscall
SYSRET: Syscall return
IRQ: HW interrupt/trap/fault
INT: SW interrupt
IRET: Return from interrupt
FAR_BRANCH: Others not generic branch type
CROSS_4K and CROSS_2M:
----------------------
They are the metrics checking for branches cross 4K or 2MB pages.
It's an approximate computing. We don't know if the area is 4K or
2MB, so always compute both.
To make the output simple, if a branch crosses 2M area, CROSS_4K
will not be incremented.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
tools/perf/builtin-report.c | 212 ++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/event.h | 4 +-
tools/perf/util/hist.c | 5 +-
3 files changed, 216 insertions(+), 5 deletions(-)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c18158b..1dc1058 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -43,6 +43,24 @@
#include <linux/bitmap.h>
#include <linux/stringify.h>
+struct branch_type_stat {
+ u64 jcc_fwd;
+ u64 jcc_bwd;
+ u64 jmp;
+ u64 ind_jmp;
+ u64 call;
+ u64 ind_call;
+ u64 ret;
+ u64 syscall;
+ u64 sysret;
+ u64 irq;
+ u64 intr;
+ u64 iret;
+ u64 far_branch;
+ u64 cross_4k;
+ u64 cross_2m;
+};
+
struct report {
struct perf_tool tool;
struct perf_session *session;
@@ -66,6 +84,7 @@ struct report {
u64 queue_size;
int socket_filter;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+ struct branch_type_stat brtype_stat;
};
static int report__config(const char *var, const char *value, void *cb)
@@ -144,6 +163,91 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
return err;
}
+static void branch_type_count(struct report *rep, struct branch_info *bi)
+{
+ struct branch_type_stat *stat = &rep->brtype_stat;
+ struct branch_flags *flags = &bi->flags;
+
+ switch (flags->type) {
+ case PERF_BR_JCC_FWD:
+ stat->jcc_fwd++;
+ break;
+
+ case PERF_BR_JCC_BWD:
+ stat->jcc_bwd++;
+ break;
+
+ case PERF_BR_JMP:
+ stat->jmp++;
+ break;
+
+ case PERF_BR_IND_JMP:
+ stat->ind_jmp++;
+ break;
+
+ case PERF_BR_CALL:
+ stat->call++;
+ break;
+
+ case PERF_BR_IND_CALL:
+ stat->ind_call++;
+ break;
+
+ case PERF_BR_RET:
+ stat->ret++;
+ break;
+
+ case PERF_BR_SYSCALL:
+ stat->syscall++;
+ break;
+
+ case PERF_BR_SYSRET:
+ stat->sysret++;
+ break;
+
+ case PERF_BR_IRQ:
+ stat->irq++;
+ break;
+
+ case PERF_BR_INT:
+ stat->intr++;
+ break;
+
+ case PERF_BR_IRET:
+ stat->iret++;
+ break;
+
+ case PERF_BR_FAR_BRANCH:
+ stat->far_branch++;
+ break;
+
+ default:
+ break;
+ }
+
+ if (flags->cross == PERF_BR_CROSS_2M)
+ stat->cross_2m++;
+ else if (flags->cross == PERF_BR_CROSS_4K)
+ stat->cross_4k++;
+}
+
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+ struct addr_location *al __maybe_unused,
+ bool single __maybe_unused,
+ void *arg)
+{
+ struct hist_entry *he = iter->he;
+ struct report *rep = arg;
+ struct branch_info *bi;
+
+ if (sort__mode == SORT_MODE__BRANCH) {
+ bi = he->branch_info;
+ branch_type_count(rep, bi);
+ }
+
+ return 0;
+}
+
static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -182,6 +286,8 @@ static int process_sample_event(struct perf_tool *tool,
*/
if (!sample->branch_stack)
goto out_put;
+
+ iter.add_entry_cb = hist_iter__branch_callback;
iter.ops = &hist_iter_branch;
} else if (rep->mem_mode) {
iter.ops = &hist_iter_mem;
@@ -369,6 +475,107 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
return ret + fprintf(fp, "\n#\n");
}
+static void branch_type_stat_display(FILE *fp, struct branch_type_stat *stat)
+{
+ u64 total = 0;
+
+ total += stat->jcc_fwd;
+ total += stat->jcc_bwd;
+ total += stat->jmp;
+ total += stat->ind_jmp;
+ total += stat->call;
+ total += stat->ind_call;
+ total += stat->ret;
+ total += stat->syscall;
+ total += stat->sysret;
+ total += stat->irq;
+ total += stat->intr;
+ total += stat->iret;
+ total += stat->far_branch;
+
+ if (total == 0)
+ return;
+
+ fprintf(fp, "\n#");
+ fprintf(fp, "\n# Branch Statistics:");
+ fprintf(fp, "\n#");
+
+ if (stat->jcc_fwd > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "JCC forward",
+ 100.0 * (double)stat->jcc_fwd / (double)total);
+
+ if (stat->jcc_bwd > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "JCC backward",
+ 100.0 * (double)stat->jcc_bwd / (double)total);
+
+ if (stat->jmp > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "JMP",
+ 100.0 * (double)stat->jmp / (double)total);
+
+ if (stat->ind_jmp > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "IND_JMP",
+ 100.0 * (double)stat->ind_jmp / (double)total);
+
+ if (stat->call > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "CALL",
+ 100.0 * (double)stat->call / (double)total);
+
+ if (stat->ind_call > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "IND_CALL",
+ 100.0 * (double)stat->ind_call / (double)total);
+
+ if (stat->ret > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "RET",
+ 100.0 * (double)stat->ret / (double)total);
+
+ if (stat->syscall > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "SYSCALL",
+ 100.0 * (double)stat->syscall / (double)total);
+
+ if (stat->sysret > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "SYSRET",
+ 100.0 * (double)stat->sysret / (double)total);
+
+ if (stat->irq > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "IRQ",
+ 100.0 * (double)stat->irq / (double)total);
+
+ if (stat->intr > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "INT",
+ 100.0 * (double)stat->intr / (double)total);
+
+ if (stat->iret > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "IRET",
+ 100.0 * (double)stat->iret / (double)total);
+
+ if (stat->far_branch > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "FAR_BRANCH",
+ 100.0 * (double)stat->far_branch / (double)total);
+
+ if (stat->cross_4k > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "CROSS_4K",
+ 100.0 * (double)stat->cross_4k / (double)total);
+
+ if (stat->cross_2m > 0)
+ fprintf(fp, "\n%12s: %5.1f%%",
+ "CROSS_2M",
+ 100.0 * (double)stat->cross_2m / (double)total);
+}
+
static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
struct report *rep,
const char *help)
@@ -404,6 +611,9 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
perf_read_values_destroy(&rep->show_threads_values);
}
+ if (sort__mode == SORT_MODE__BRANCH)
+ branch_type_stat_display(stdout, &rep->brtype_stat);
+
return 0;
}
@@ -936,6 +1146,8 @@ int cmd_report(int argc, const char **argv)
if (has_br_stack && branch_call_mode)
symbol_conf.show_branchflag_count = true;
+ memset(&report.brtype_stat, 0, sizeof(struct branch_type_stat));
+
/*
* Branch mode is a tristate:
* -1 means default, so decide based on the file having branch data.
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index eb7a7b2..b192a10 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -142,7 +142,9 @@ struct branch_flags {
u64 in_tx:1;
u64 abort:1;
u64 cycles:16;
- u64 reserved:44;
+ u64 type:4;
+ u64 cross:2;
+ u64 reserved:38;
};
struct branch_entry {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 61bf304..c8aee25 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -745,12 +745,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
}
static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter,
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
struct addr_location *al __maybe_unused)
{
- /* to avoid calling callback function */
- iter->he = NULL;
-
return 0;
}
--
2.7.4
next prev parent reply other threads:[~2017-04-07 2:50 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-07 10:47 [PATCH v2 0/5] perf report: Show branch type Jin Yao
2017-04-07 10:47 ` [PATCH v2 1/5] perf/core: Define the common branch type classification Jin Yao
2017-04-07 10:47 ` [PATCH v2 2/5] perf/x86/intel: Record branch type Jin Yao
2017-04-07 15:20 ` Peter Zijlstra
2017-04-07 16:48 ` Andi Kleen
2017-04-07 17:20 ` Peter Zijlstra
2017-04-07 17:50 ` Andi Kleen
2017-04-08 8:46 ` Jin, Yao
2017-04-07 10:47 ` [PATCH v2 3/5] perf record: Create a new option save_type in --branch-filter Jin Yao
2017-04-07 10:47 ` Jin Yao [this message]
2017-04-07 10:47 ` [PATCH v2 5/5] perf report: Show branch type in callchain entry Jin Yao
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=1491562066-7472-5-git-send-email-yao.jin@linux.intel.com \
--to=yao.jin@linux.intel.com \
--cc=Linux-kernel@vger.kernel.org \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@intel.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=yao.jin@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;
as well as URLs for NNTP newsgroup(s).